INDEX

Explanations

statements related to affirming accountability or responsibility

oai_token-act-pair · gpt-3.5-turbo

direct quotations and speech within the text

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

Negative Logits

 exceptions

-0.76

 anyway

-0.72

 transgress

-0.71

 nonex

-0.69

 pretext

-0.69

 pretended

-0.67

 endif

-0.67

 pretend

-0.66

 nonexistent

-0.66

 undefined

-0.65

POSITIVE LOGITS

Congratulations

1.25

 Congratulations

1.12

 thrilled

1.04

 delighted

0.99

 congratulations

0.96

 congratulate

0.96

 pleased

0.95

htaking

0.92

 saddened

0.90

Cong

0.89

Activations Density 0.527%

statements related to affirming accountability or responsibility

direct quotations and speech within the text

No Known Activations