INDEX

Explanations

personal pronouns followed by the word 'said'

oai_token-act-pair · gpt-3.5-turbo

references to a specific male speaker or individual

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

noon

-0.85

 privile

-0.74

evidence

-0.64

requisite

-0.62

 Sorce

-0.62

etheless

-0.62

rocket

-0.61

 numbering

-0.59

 locating

-0.59

liter

-0.59

POSITIVE LOGITS

 said

1.42

 wrote

1.28

 joked

1.27

 says

1.23

 explained

1.19

 told

1.19

 exclaimed

1.17

 replied

1.16

 tweeted

1.15

 remarked

1.11

Activations Density 0.066%

personal pronouns followed by the word 'said'

references to a specific male speaker or individual

No Comments

No Known Activations