INDEX

Explanations

information or items that have been obtained or acquired

oai_token-act-pair · gpt-3.5-turbo

terms associated with acquiring or obtaining information or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

meg

-0.56

idth

-0.55

atever

-0.55

mare

-0.54

 odds

-0.52

 seriousness

-0.51

 multinational

-0.51

tons

-0.51

tan

-0.50

NCT

-0.50

POSITIVE LOGITS

 from

1.01

via

1.00

 through

0.93

 during

0.93

from

0.83

 anecd

0.83

by

0.83

 anonymously

0.80

 FROM

0.78

iasco

0.77

Activations Density 0.202%

information or items that have been obtained or acquired

terms associated with acquiring or obtaining information or items

No Comments

No Known Activations