INDEX

Explanations

expressions related to showing approval or disapproval

oai_token-act-pair · gpt-3.5-turbo

references to "thumbs" and related expressions of approval or disapproval

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Occupations

-0.76

mingham

-0.75

Ø§ÙĦ

-0.73

hammad

-0.73

iveness

-0.70

places

-0.70

ÙĦ

-0.70

ulkan

-0.69

Downloadha

-0.68

urity

-0.67

POSITIVE LOGITS

 thumb

1.09

hole

0.83

print

0.81

eenth

0.79

sticks

0.79

wheel

0.79

pad

0.79

tie

0.78

tip

0.77

 finger

0.77

Activations Density 0.018%

expressions related to showing approval or disapproval

references to "thumbs" and related expressions of approval or disapproval

No Comments

No Known Activations