INDEX

Explanations

phrases indicating possession or ownership

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "have" and its variations

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

catentry

-0.66

RESULTS

-0.59

aths

-0.55

BuyableInstoreAndOnline

-0.53

 Reload

-0.53

esp

-0.53

ERY

-0.52

ERAL

-0.52

err

-0.52

 Shock

-0.52

POSITIVE LOGITS

 mastered

1.01

 amassed

0.99

 been

0.98

 gotten

0.98

 devised

0.97

 seen

0.96

 undertaken

0.92

 encountered

0.91

 accumulated

0.90

 learnt

0.89

Activations Density 0.084%

phrases indicating possession or ownership

the repeated use of the word "have" and its variations

No Comments

No Known Activations