INDEX

Explanations

phrases or words related to something notorious or infamous

oai_token-act-pair · gpt-3.5-turbo

terms related to individuals or entities described as notorious or infamous

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ynthesis

-0.72

PT

-0.72

avers

-0.71

vet

-0.70

adra

-0.70

strings

-0.69

claimer

-0.69

dh

-0.68

cos

-0.67

joice

-0.67

POSITIVE LOGITS

 infamous

0.81

 notorious

0.79

 metic

0.78

 culprit

0.78

 offender

0.75

ebin

0.72

 dirty

0.70

 scourge

0.68

 dictator

0.67

 misuse

0.66

Activations Density 0.017%

phrases or words related to something notorious or infamous

terms related to individuals or entities described as notorious or infamous

No Comments

No Known Activations