INDEX

Explanations

mentions of popularity or trends

oai_token-act-pair · gpt-3.5-turbo

references to popularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

erm

-0.75

uran

-0.72

sonian

-0.69

alk

-0.66

 Dull

-0.63

aer

-0.62

 Neurolog

-0.62

 intest

-0.61

 Shell

-0.61

rib

-0.60

POSITIVE LOGITS

ately

0.87

ability

0.85

rise

0.82

quo

0.78

iqueness

0.74

hare

0.74

acy

0.73

achi

0.71

ously

0.70

ante

0.69

Activations Density 0.042%

mentions of popularity or trends

references to popularity

No Comments

No Known Activations