INDEX

Explanations

proper nouns or names related to various individuals

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of a specific term or name

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

geoning

-0.78

ition

-0.75

itional

-0.72

mbuds

-0.72

akening

-0.72

tale

-0.71

abulary

-0.66

istani

-0.66

kered

-0.66

rafted

-0.66

POSITIVE LOGITS

inem

0.88

 Zeit

0.79

ussen

0.78

ONSORED

0.76

Zo

0.73

ãĤ´ãĥ³

0.73

icro

0.67

geist

0.66

Spect

0.65

è£ħ

0.64

Activations Density 0.042%

proper nouns or names related to various individuals

repeated mentions of a specific term or name

No Comments

No Known Activations