INDEX

Explanations

the name "Wilson" at different contexts

oai_token-act-pair · gpt-3.5-turbo

references to the name "Wilson."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Rated

-0.73

plate

-0.72

hot

-0.71

aft

-0.71

plates

-0.69

Lex

-0.66

onial

-0.66

glomer

-0.63

otten

-0.63

ngth

-0.63

POSITIVE LOGITS

 Chandler

0.83

ston

0.82

ufact

0.78

sey

0.78

 Ramos

0.78

 Oaks

0.76

 Wilson

0.76

 Pinball

0.71

igans

0.71

istically

0.70

Activations Density 0.035%

the name "Wilson" at different contexts

references to the name "Wilson."

No Comments

No Known Activations