INDEX

Explanations

mentions of the word "lion" along with a high activation value

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "lion."

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

mble

-0.89

ACTION

-0.80

chell

-0.79

ilk

-0.78

Ñı

-0.75

lying

-0.74

matter

-0.69

ETH

-0.66

ÑĮ

-0.66

skirts

-0.65

POSITIVE LOGITS

esses

1.25

fish

1.08

ess

1.00

eye

0.96

 lions

0.96

ous

0.88

osaurs

0.85

odon

0.84

doms

0.84

iasis

0.83

Activations Density 0.018%

mentions of the word "lion" along with a high activation value

repeated mentions of the word "lion."

No Comments

No Known Activations