INDEX

Explanations

phrases where someone is quoted speaking

oai_token-act-pair · gpt-3.5-turbo

instances of the pronoun "he" indicating a speaker or subject in discourse

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

lihood

-0.78

 privile

-0.71

 miscarriage

-0.66

Measure

-0.65

selection

-0.62

 disproportion

-0.60

 bookmark

-0.60

 caliber

-0.59

ãĥĳ

-0.57

 locating

-0.56

POSITIVE LOGITS

 said

1.32

 told

1.30

 joked

1.18

 wrote

1.17

 explained

1.16

 says

1.13

 remarked

1.10

said

1.06

 exclaimed

1.05

 tweeted

1.04

Activations Density 0.056%

phrases where someone is quoted speaking

instances of the pronoun "he" indicating a speaker or subject in discourse

No Comments

No Known Activations