INDEX

Explanations

words related to specific locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the comma punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 comprom

-0.70

 abusers

-0.65

agues

-0.63

opsy

-0.63

rophic

-0.62

rely

-0.62

agog

-0.62

 unborn

-0.61

uple

-0.60

odies

-0.59

POSITIVE LOGITS

,,,,

0.97

tel

0.87

,,,,,,,,

0.85

taboola

0.79

 Canary

0.79

tein

0.78

;;;;

0.78

then

0.77

;;;;;;;;

0.77

],

0.74

Activations Density 0.016%

words related to specific locations

occurrences of the comma punctuation

No Comments

No Known Activations