INDEX

Explanations

names of government official positions

oai_token-act-pair · gpt-3.5-turbo

mentions of government officials and their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Äĩ

-0.85

worldly

-0.77

liga

-0.76

pole

-0.73

EStreamFrame

-0.71

eros

-0.70

nikov

-0.65

bol

-0.65

 panc

-0.64

esville

-0.63

POSITIVE LOGITS

 Eric

0.93

 Susan

0.91

 Janet

0.90

 Cher

0.89

Cec

0.89

 Michael

0.88

 David

0.87

 Steven

0.87

 Mike

0.87

 Ernest

0.85

Activations Density 0.097%

names of government official positions

mentions of government officials and their titles

No Comments

No Known Activations