INDEX

Explanations

the word "food" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to food and edible items

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

 Constantin

-0.79

urity

-0.68

ISTER

-0.66

asper

-0.65

isters

-0.65

MIA

-0.65

 Asheville

-0.64

agne

-0.64

chal

-0.63

APE

-0.63

POSITIVE LOGITS

lers

1.06

yssey

0.97

ood

0.96

edly

0.94

irect

0.94

ler

0.91

0.89

ed

0.88

roid

0.88

ragon

0.87

Activations Density 0.044%

the word "food" in various contexts

references to food and edible items

No Comments

No Known Activations