INDEX

Explanations

quotes or reported speech

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "told."

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

 ILCS

-0.98

é¾įåĸļå£«

-0.71

mol

-0.70

ãĤ¦ãĤ¹

-0.70

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.70

Û

-0.68

angular

-0.66

artifacts

-0.65

terms

-0.65

ItemThumbnailImage

-0.65

POSITIVE LOGITS

 reporters

1.70

 interviewer

1.24

 listeners

1.24

 journalists

1.21

 viewers

1.14

 attendees

1.14

CNN

1.14

 MSNBC

1.13

 senators

1.11

 lawmakers

1.10

Activations Density 0.103%

quotes or reported speech

phrases that include the word "told."

No Comments

No Known Activations