INDEX

Explanations

references to a specific person named Nancy Pelosi

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Nancy" in various contexts

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

tered

-0.76

orescent

-0.76

ioch

-0.76

orical

-0.75

upon

-0.75

points

-0.73

orically

-0.73

=-=-=-=-

-0.72

oric

-0.72

oning

-0.71

POSITIVE LOGITS

 Pelosi

1.25

 Drew

0.90

 Reagan

0.88

 Grace

0.87

Lan

0.82

 McMahon

0.78

 Claus

0.72

Mae

0.72

 Jane

0.72

 Maria

0.71

Activations Density 0.016%

references to a specific person named Nancy Pelosi

mentions of the name "Nancy" in various contexts

No Comments

No Known Activations