INDEX

Explanations

names of individuals with varying levels of importance

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Hispan

-0.68

 Slovenia

-0.67

 Hornets

-0.67

 Clarkson

-0.65

 spoiler

-0.65

 Brav

-0.63

 Catalonia

-0.62

 overload

-0.61

 narrowing

-0.59

 Sloven

-0.59

POSITIVE LOGITS

Jr

1.12

nr

0.91

uez

0.88

III

0.83

Sr

0.82

inguished

0.81

ensen

0.79

fman

0.79

itars

0.78

grave

0.78

Activations Density 0.234%

names of individuals with varying levels of importance

proper nouns, particularly names of people

No Comments

No Known Activations