INDEX

Explanations

definitions or actions related to the word "bust."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "bust" in various contexts

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

velength

-0.83

THER

-0.73

 vomit

-0.69

 Rouge

-0.69

nsic

-0.69

termination

-0.68

esthetic

-0.66

WAYS

-0.66

perse

-0.66

asonable

-0.65

POSITIVE LOGITS

 bust

1.14

 Bust

0.95

endor

0.87

buster

0.86

enance

0.85

outs

0.85

sd

0.83

neck

0.82

aign

0.81

Activations Density 0.013%

definitions or actions related to the word "bust."

instances of the word "bust" in various contexts

No Comments

No Known Activations