INDEX

Explanations

descriptions of importance or roles in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the roles and importance of various subjects or entities in different 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

isa

-0.73

ETA

-0.70

MpServer

-0.67

Eva

-0.64

aiden

-0.64

river

-0.63

mort

-0.62

bart

-0.62

APTER

-0.62

FIN

-0.62

POSITIVE LOGITS

fulness

0.88

 inherent

0.83

lessness

0.77

itability

0.72

 dangers

0.70

of

0.69

 role

0.69

OF

0.67

 hazards

0.67

 exerted

0.65

Activations Density 0.136%

descriptions of importance or roles in various contexts

references to the roles and importance of various subjects or entities in different contexts

No Comments

No Known Activations