INDEX

Explanations

phrases indicating a component or element of a broader context

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a relationship to a larger context or group

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 sparks

-0.72

oons

-0.70

 candles

-0.70

eers

-0.68

ukong

-0.68

arten

-0.66

arians

-0.65

aughs

-0.65

 Akin

-0.64

 vampires

-0.64

POSITIVE LOGITS

 larger

0.95

 equation

0.88

 continuum

0.83

 ecosystem

0.80

 broader

0.78

 wider

0.76

 province

0.73

 realm

0.73

 matrix

0.71

 arrangement

0.70

Activations Density 0.122%

phrases indicating a component or element of a broader context

phrases indicating a relationship to a larger context or group

No Comments

No Known Activations