INDEX

Explanations

websites or URLs

oai_token-act-pair · gpt-3.5-turbo

web addresses or URLs

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

ï¸ı

-0.76

 corrective

-0.64

 Â«

-0.63

 Eighth

-0.63

 Gian

-0.62

 Scheme

-0.62

ï¸

-0.62

 Goldberg

-0.61

 Racial

-0.61

FAC

-0.60

POSITIVE LOGITS

cdn

1.01

online

0.94

ecd

0.92

/?

0.86

amazon

0.85

biz

0.83

pedia

0.82

tv

0.79

alg

0.77

research

0.75

Activations Density 0.062%

websites or URLs

web addresses or URLs

No Comments

No Known Activations