INDEX

Explanations

measurements or quantities indicated by a number followed by a unit of measurement

oai_token-act-pair · gpt-3.5-turbo

numerical data related to quantities and measurements

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

£ı

-0.68

Reviewer

-0.65

 Exodus

-0.64

 vanity

-0.64

liction

-0.62

 thesis

-0.62

 vain

-0.60

 fame

-0.60

 Heller

-0.60

 arena

-0.59

POSITIVE LOGITS

Â½

1.26

 Â½

0.99

0.95

PO

0.91

0.90

0.89

Â¢

0.83

bp

0.83

Activations Density 0.188%

measurements or quantities indicated by a number followed by a unit of measurement

numerical data related to quantities and measurements

No Comments

No Known Activations