INDEX

Explanations

words related to physical locations or groups of people affiliated with certain cultures

oai_token-act-pair · gpt-3.5-turbo

references to linguistic characteristics or grammatical structures related to the English language

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

externalActionCode

-0.95

achine

-0.76

aceae

-0.63

taboola

-0.61

utical

-0.61

atche

-0.60

enance

-0.60

ooters

-0.59

natureconservancy

-0.58

 lifespan

-0.57

POSITIVE LOGITS

oland

0.86

aston

0.69

rette

0.64

una

0.64

umeric

0.63

Pacific

0.61

wine

0.60

stadt

0.60

ifa

0.58

uria

0.58

Activations Density 0.168%

words related to physical locations or groups of people affiliated with certain cultures

references to linguistic characteristics or grammatical structures related to the English language

No Comments

No Known Activations