INDEX

Explanations

references to emails and servers related to Hillary Clinton's email controversy

oai_token-act-pair · gpt-3.5-turbo

references to Hillary Clinton's email server and related terms regarding private communications

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

umar

-0.82

ksh

-0.79

Wim

-0.75

STAR

-0.75

axis

-0.73

KR

-0.72

 Dudley

-0.72

NT

-0.70

UP

-0.70

erenn

-0.69

POSITIVE LOGITS

 Clinton

0.92

 trove

0.88

ghazi

0.87

umenthal

0.87

 aides

0.84

 scandals

0.83

Clinton

0.82

 Hillary

0.80

 aide

0.80

 dumps

0.80

Activations Density 0.059%

references to emails and servers related to Hillary Clinton's email controversy

references to Hillary Clinton's email server and related terms regarding private communications

No Comments

No Known Activations