INDEX

Explanations

mentions of the word "gin"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "gin."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

gypt

-0.79

iscopal

-0.62

mediated

-0.62

 Difficulty

-0.61

 complication

-0.60

 accomplishment

-0.60

 paternity

-0.60

 creep

-0.60

 Setting

-0.60

 Difference

-0.59

POSITIVE LOGITS

gin

1.29

uine

1.12

fo

0.94

oline

0.91

forth

0.89

uin

0.87

raphic

0.87

otten

0.85

Ò

0.85

herer

0.83

Activations Density 0.020%

mentions of the word "gin"

instances of the word "gin."

No Comments

No Known Activations