INDEX

Explanations

words related to emphasis or clarification of a statement, often indicating a contrast between appearances and reality

oai_token-act-pair · gpt-3.5-turbo

words that indicate clarification or contradiction of a statement

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

regate

-0.83

inav

-0.72

enaries

-0.71

idences

-0.69

might

-0.69

ortmund

-0.68

 Awakens

-0.68

rug

-0.66

doms

-0.65

would

-0.65

POSITIVE LOGITS

 synonymous

0.95

 supposed

0.93

 irrelevant

0.93

 considered

0.93

 indicative

0.93

 incompatible

0.90

 regarded

0.89

 going

0.88

 problematic

0.87

 worth

0.87

Activations Density 0.281%

words related to emphasis or clarification of a statement, often indicating a contrast between appearances and reality

words that indicate clarification or contradiction of a statement

No Comments

No Known Activations