INDEX

Explanations

mentions of the name "Hillary Clinton"

oai_token-act-pair · gpt-3.5-turbo

mentions of Hillary Clinton

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

otal

-0.68

CONCLUS

-0.67

Member

-0.66

iple

-0.64

 DRAG

-0.62

âķĲ

-0.61

pec

-0.60

ribune

-0.60

trl

-0.60

POSITIVE LOGITS

 Rodham

1.53

 Clinton

1.52

Clinton

1.27

clinton

1.20

 Clintons

1.10

INTON

1.10

 Hillary

1.04

 Supporters

0.93

 Diane

0.92

Hillary

0.92

Activations Density 0.018%

mentions of the name "Hillary Clinton"

mentions of Hillary Clinton

No Comments

No Known Activations