INDEX

Explanations

locations or places mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

the word "near."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

BILL

-0.76

Percent

-0.73

alian

-0.70

oleon

-0.69

zhen

-0.66

gear

-0.66

Upload

-0.65

strong

-0.65

Written

-0.64

ãĥīãĥ©

-0.64

POSITIVE LOGITS

shore

0.96

 shore

0.82

 Bethlehem

0.82

 Interstate

0.80

 Damascus

0.79

sighted

0.78

 airports

0.78

 midnight

0.78

 campus

0.77

 Calais

0.77

Activations Density 0.045%

locations or places mentioned in the text

the word "near."

No Comments

No Known Activations