INDEX

Explanations

mentions of the term "Wild"

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the term "Wild" 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

 mathemat

-0.88

akeru

-0.79

auga

-0.78

uters

-0.77

uckland

-0.75

ounced

-0.73

ially

-0.72

abeth

-0.71

acies

-0.70

 tremend

-0.70

POSITIVE LOGITS

erness

0.98

lings

0.98

rose

0.91

fires

0.89

Aid

0.89

flower

0.88

fire

0.87

Tang

0.85

skin

0.85

lord

0.81

Activations Density 0.008%

mentions of the term "Wild"

the repeated mention of the term "Wild" in various contexts

No Comments

No Known Activations