INDEX

Explanations

phrases or words related to testing, examinations, or trials

oai_token-act-pair · gpt-3.5-turbo

references to testing or assessments

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

theless

-0.86

ignt

-0.81

VIDIA

-0.73

etheless

-0.72

cedented

-0.68

Ëľ

-0.65

ecause

-0.65

bernatorial

-0.65

SOURCE

-0.64

nuts

-0.64

POSITIVE LOGITS

osterone

1.36

imony

1.33

imon

1.06

icular

0.98

icles

0.97

ifies

0.92

icle

0.89

aments

0.87

udo

0.86

su

0.78

Activations Density 0.028%

phrases or words related to testing, examinations, or trials

references to testing or assessments

No Comments

No Known Activations