INDEX

Explanations

phrases expressing comparison or addition

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate agreement or affirmation

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

avorite

-0.61

anu

-0.61

cffff

-0.60

ovo

-0.59

AME

-0.59

kefeller

-0.58

 separation

-0.55

 monop

-0.55

/"

-0.53

appro

-0.53

POSITIVE LOGITS

as

0.88

inda

0.79

 vers

0.79

 suited

0.72

INGTON

0.71

 known

0.70

abeth

0.66

esley

0.65

founded

0.64

nesses

0.64

Activations Density 0.029%

phrases expressing comparison or addition

phrases that indicate agreement or affirmation

No Comments

No Known Activations