INDEX

Explanations

references to the name "Clinton"

oai_token-act-pair · gpt-3.5-turbo

references to 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

teenth

-0.79

lass

-0.78

Reviewer

-0.76

GGGGGGGG

-0.73

 Flavoring

-0.71

DIS

-0.71

ANK

-0.71

ÏĦ

-0.70

semble

-0.70

gered

-0.69

POSITIVE LOGITS

 Clinton

1.04

Clinton

0.98

INTON

0.95

clinton

0.86

mia

0.85

istas

0.84

 Hillary

0.83

 Supporters

0.82

 impeachment

0.81

ite

0.81

Activations Density 0.026%

references to the name "Clinton"

references to Hillary Clinton

No Comments

No Known Activations