INDEX

Explanations

phrases related to ongoing activities or changes

oai_token-act-pair · gpt-3.5-turbo

phrases related to actions of people in positions of authority

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 predecessor

-0.54

TION

-0.54

isSpecialOrderable

-0.52

 Kills

-0.52

 Brazilian

-0.51

 presidency

-0.50

 Nato

-0.49

 Width

-0.48

ç«

-0.48

was

-0.48

POSITIVE LOGITS

 themselves

1.26

selves

0.96

 their

0.83

their

0.83

 THEIR

0.82

 theirs

0.81

 yourselves

0.77

 Their

0.70

joice

0.67

Their

0.67

Activations Density 1.159%

phrases related to ongoing activities or changes

phrases related to actions of people in positions of authority

No Comments

No Known Activations