INDEX

Explanations

proper nouns or names of individuals

oai_token-act-pair · gpt-3.5-turbo

terms related to validation or justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

cular

-0.88

cule

-0.77

pmwiki

-0.71

pec

-0.70

senal

-0.70

asers

-0.69

cules

-0.64

ps

-0.63

cone

-0.63

 cytok

-0.62

POSITIVE LOGITS

 Kejriwal

1.16

icators

0.94

ictive

0.93

sson

0.87

vind

0.86

icator

0.86

ication

0.85

icates

0.80

icious

0.80

icate

0.80

Activations Density 0.008%

proper nouns or names of individuals

terms related to validation or justification

No Comments

No Known Activations