INDEX

Explanations

negative, critical, or opposing adjectives

oai_token-act-pair · gpt-3.5-turbo

phrases related to negative descriptors or conditions associated with failures or mistakes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 antioxid

-0.77

 guiActiveUnfocused

-0.76

 Merge

-0.75

ħĭ

-0.70

 Authors

-0.69

 Beaut

-0.68

 Puzzles

-0.66

Valid

-0.66

lisher

-0.65

soType

-0.65

POSITIVE LOGITS

gotten

0.94

rious

0.73

utton

0.65

itably

0.63

abet

0.63

Beck

0.63

ady

0.62

eeds

0.62

Syd

0.62

 Desire

0.62

Activations Density 0.052%

negative, critical, or opposing adjectives

phrases related to negative descriptors or conditions associated with failures or mistakes

No Comments

No Known Activations