INDEX

Explanations

words related to harmful or dangerous actions or objects

oai_token-act-pair · gpt-3.5-turbo

references to specific objects or 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

Const

-0.73

Surv

-0.68

 Canad

-0.67

Critical

-0.67

 Feder

-0.66

Effective

-0.66

vern

-0.65

umat

-0.65

 misunder

-0.65

ocial

-0.65

POSITIVE LOGITS

 bike

0.83

 shoe

0.80

 carriage

0.79

 pistol

0.78

 camel

0.75

 cylinder

0.74

bucks

0.73

 rifle

0.73

bike

0.73

axe

0.73

Activations Density 0.429%

words related to harmful or dangerous actions or objects

references to specific objects or items

No Comments

No Known Activations