INDEX

Explanations

phrases involving pseudonyms or alternate names

oai_token-act-pair · gpt-3.5-turbo

references to different pseudonyms or aliases

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

hement

-0.78

SPONSORED

-0.78

asy

-0.77

itives

-0.77

actly

-0.76

ibur

-0.74

TB

-0.73

reement

-0.72

ETF

-0.70

rera

-0.67

POSITIVE LOGITS

products

0.97

 virtue

0.85

 unnoticed

0.82

laws

0.81

product

0.79

 afar

0.74

 leaps

0.71

 fiat

0.70

 multiplying

0.69

catch

0.69

Activations Density 0.111%

phrases involving pseudonyms or alternate names

references to different pseudonyms or aliases

No Comments

No Known Activations