INDEX

Explanations

indicators related to individual people

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals, highlighting their roles and significance in various contexts

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

 Silence

-0.72

 Horses

-0.69

UV

-0.66

 Scroll

-0.65

 Lann

-0.64

 Britann

-0.64

ãĥ¥

-0.63

LV

-0.63

 Norton

-0.63

PER

-0.62

POSITIVE LOGITS

ividual

1.13

istically

0.99

 identifiable

0.91

ities

0.89

ortium

0.88

istic

0.87

istics

0.83

 composing

0.82

who

0.80

ized

0.79

Activations Density 0.024%

indicators related to individual people

mentions of individuals, highlighting their roles and significance in various contexts

No Comments

No Known Activations