INDEX

Explanations

instances of distribution of various items or information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "distributed."

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

chest

-0.79

ABE

-0.78

olds

-0.71

glers

-0.70

oenix

-0.66

hma

-0.66

astical

-0.65

ton

-0.65

gery

-0.64

tes

-0.64

POSITIVE LOGITS

 distributing

0.95

 distribute

0.95

 distribut

0.93

 distribution

0.92

 leaflets

0.91

 distributions

0.91

 ledger

0.87

 disperse

0.85

DAQ

0.85

 distributed

0.83

Activations Density 0.014%

instances of distribution of various items or information

occurrences of the word "distributed."

No Comments

No Known Activations