INDEX

Explanations

instances of the word "test" along with associated verbs and nouns indicating experimentation or assessment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "test" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lance

-0.79

SOURCE

-0.75

CENT

-0.74

cember

-0.73

apo

-0.72

brance

-0.71

atto

-0.69

MpServer

-0.69

nick

-0.66

ppa

-0.65

POSITIVE LOGITS

 whether

1.12

 hypotheses

1.11

osterone

0.93

whether

0.80

 feasibility

0.80

 viability

0.76

 positive

0.76

orously

0.75

ifies

0.75

out

0.72

Activations Density 0.051%

instances of the word "test" along with associated verbs and nouns indicating experimentation or assessment

instances of the word "test" and its variations

No Comments

No Known Activations