INDEX

Explanations

locations or geographic regions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "and" in various contexts

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

Sov

-0.76

lash

-0.75

HK

-0.74

BIL

-0.70

>[

-0.68

ict

-0.67

inct

-0.66

eton

-0.66

DragonMagazine

-0.65

======

-0.64

POSITIVE LOGITS

 thereby

0.96

 thus

0.95

 consequently

0.94

 hence

0.93

 thence

0.90

 vicinity

0.88

 secondly

0.86

 therefore

0.84

 vice

0.83

 then

0.83

Activations Density 0.545%

locations or geographic regions

instances of the word "and" in various contexts

No Comments

No Known Activations