INDEX

Explanations

mentions of thumbs used metaphorically or literally in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to thumbs or thumb-related phrases

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

iveness

-0.71

mingham

-0.70

 Occupations

-0.69

places

-0.69

Ø§ÙĦ

-0.68

zona

-0.68

RT

-0.68

effic

-0.66

ively

-0.66

anyahu

-0.66

POSITIVE LOGITS

 thumb

1.02

eenth

0.91

print

0.89

stick

0.84

hole

0.82

sticks

0.82

pad

0.81

prints

0.80

tie

0.79

tip

0.77

Activations Density 0.031%

mentions of thumbs used metaphorically or literally in various contexts

references to thumbs or thumb-related phrases

No Comments

No Known Activations