INDEX

Explanations

words related to political figures or entities

oai_token-act-pair · gpt-3.5-turbo

references to the term "CM" or its variations in a variety of 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.87

 sidx

-0.78

gered

-0.75

enced

-0.75

ggies

-0.73

rets

-0.71

*/(

-0.71

reys

-0.70

ibility

-0.70

gew

-0.69

POSITIVE LOGITS

 Punk

0.86

ODE

0.81

ageddon

0.80

ancel

0.79

illon

0.79

ahon

0.77

trop

0.71

apper

0.71

ichael

0.67

ography

0.66

Activations Density 0.022%

words related to political figures or entities

references to the term "CM" or its variations in a variety of contexts

No Comments

No Known Activations