INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to locations and places

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

 positives

-0.70

 crop

-0.63

 contingency

-0.63

 failings

-0.61

 successes

-0.58

ÃįÃį

-0.57

 pleasures

-0.56

 TOUR

-0.56

 burner

-0.56

 setbacks

-0.55

POSITIVE LOGITS

ensis

0.79

ario

0.76

 Junction

0.75

ibia

0.73

Tib

0.70

 respectively

0.67

opolis

0.66

fecture

0.65

 suburb

0.65

hess

0.65

Activations Density 0.439%

locations or places

proper nouns related to locations and places

No Comments

No Known Activations