INDEX

Explanations

instances of "applies to" statements

oai_token-act-pair · gpt-3.5-turbo

phrases that express applicability or relevance to specific subjects or scenarios

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

erd

-0.80

iev

-0.76

achev

-0.73

icter

-0.72

urat

-0.67

arov

-0.67

itchie

-0.66

riber

-0.66

Champ

-0.66

ileaks

-0.66

POSITIVE LOGITS

ALL

0.94

 EVERY

0.91

all

0.86

 everyone

0.86

 everything

0.84

 every

0.84

 everybody

0.83

 ours

0.76

etheless

0.74

 both

0.74

Activations Density 0.341%

instances of "applies to" statements

phrases that express applicability or relevance to specific subjects or scenarios

No Comments

No Known Activations