INDEX

Explanations

the word "gorilla" appearing in various contexts

oai_token-act-pair · gpt-3.5-turbo

variations of the word "gorilla."

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

iosyn

-0.83

ply

-0.83

paren

-0.76

orough

-0.75

leness

-0.75

matically

-0.74

den

-0.73

recomm

-0.72

log

-0.72

spot

-0.72

POSITIVE LOGITS

ieri

0.87

 Haram

0.84

istas

0.79

ength

0.78

 Ammunition

0.76

esi

0.75

 Rica

0.73

illas

0.69

izers

0.69

 Gomez

0.68

Activations Density 0.021%

the word "gorilla" appearing in various contexts

variations of the word "gorilla."

No Comments

No Known Activations