INDEX

Explanations

instances of the word "bit" followed by a value indicating significance or intensity

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a moderate or slight degree of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

inarily

-0.80

ocity

-0.79

ovies

-0.78

 Siber

-0.78

endars

-0.75

apons

-0.72

aspers

-0.72

itars

-0.71

doms

-0.70

itures

-0.70

POSITIVE LOGITS

bit

0.92

umen

0.92

 reminiscent

0.75

 peek

0.74

 prick

0.71

 chunk

0.70

terness

0.69

ener

0.68

 cryptic

0.65

swe

0.64

Activations Density 0.019%

instances of the word "bit" followed by a value indicating significance or intensity

phrases that indicate a moderate or slight degree of something

No Comments

No Known Activations