INDEX

Explanations

phrases indicating intention or purpose

oai_token-act-pair · gpt-3.5-turbo

the word "meant" in various contexts, indicating purpose or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

anon

-0.77

 Owens

-0.67

EStreamFrame

-0.67

 Carbuncle

-0.62

wine

-0.61

SPONSORED

-0.60

externalActionCode

-0.60

redo

-0.59

å£«

-0.58

Du

-0.57

POSITIVE LOGITS

lessly

0.71

reprene

0.70

erest

0.69

IENT

0.66

ERSON

0.66

âĶģ

0.65

 principally

0.64

ĸļ

0.63

Sov

0.62

 spirited

0.62

Activations Density 0.019%

phrases indicating intention or purpose

the word "meant" in various contexts, indicating purpose or intention

No Comments

No Known Activations