INDEX

Explanations

phrases indicating a contrast or emphasizing a point

oai_token-act-pair · gpt-3.5-turbo

statements of fact or significant affirmations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

LC

-0.71

oka

-0.69

oj

-0.66

apo

-0.66

tu

-0.63

unity

-0.62

rals

-0.59

riors

-0.58

rolling

-0.57

ogun

-0.56

POSITIVE LOGITS

 downright

1.16

 quite

0.88

 worse

0.81

 even

0.80

 pretty

0.78

 proverb

0.71

 envy

0.67

 opposite

0.67

 counterproductive

0.67

 almost

0.66

Activations Density 0.315%

phrases indicating a contrast or emphasizing a point

statements of fact or significant affirmations

No Comments

No Known Activations