INDEX

Explanations

the name "George"

oai_token-act-pair · gpt-3.5-turbo

references to the name "George" 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 @ 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

igslist

-0.79

endant

-0.76

odcast

-0.74

ateur

-0.72

ngth

-0.72

letal

-0.71

ansas

-0.71

aditional

-0.70

pees

-0.69

Repe

-0.68

POSITIVE LOGITS

 Orwell

0.88

 Thor

0.83

 Zimmerman

0.83

 Lucas

0.80

Cic

0.78

VI

0.76

iannopoulos

0.75

 Soros

0.74

ORGE

0.73

Clo

0.72

Activations Density 0.014%

the name "George"

references to the name "George" in various contexts

No Comments

No Known Activations