INDEX

Explanations

political figures or entities

oai_token-act-pair · gpt-3.5-turbo

key political figures and their affiliations or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

fman

-0.87

berra

-0.77

endix

-0.68

undai

-0.68

'>

-0.68

psey

-0.67

ateral

-0.66

eway

-0.65

insured

-0.65

leck

-0.64

POSITIVE LOGITS

 Roland

0.73

 Ruth

0.71

chief

0.64

 Betsy

0.63

 Rupert

0.63

 Shang

0.62

 Irma

0.62

 Shannon

0.62

aign

0.62

 Carly

0.61

Activations Density 0.707%

political figures or entities

key political figures and their affiliations or actions

No Comments

No Known Activations