INDEX

Explanations

names of people or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arial

-1.00

uate

-0.81

inates

-0.79

ially

-0.78

ional

-0.74

 sucker

-0.74

antine

-0.73

otto

-0.71

egal

-0.70

uated

-0.70

POSITIVE LOGITS

nesday

1.48

restling

0.96

tip

0.89

ashington

0.85

esome

0.82

fare

0.76

izard

0.75

edge

0.74

atts

0.74

houses

0.73

Activations Density 0.076%

names of people or places

proper nouns related to specific individuals or organizations

No Comments

No Known Activations