INDEX

Explanations

links or invitations for more information or content

oai_token-act-pair · gpt-3.5-turbo

phrases that refer to additional information or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

xtap

-0.86

Enlarge

-0.85

ader

-0.82

Cro

-0.81

DragonMagazine

-0.74

Fram

-0.74

liest

-0.73

mobi

-0.73

ãĥ¼ãĥĨãĤ£

-0.73

Disk

-0.72

POSITIVE LOGITS

 than

1.06

 information

1.00

 info

0.92

 stringent

0.87

 detailed

0.83

 adventurous

0.83

 advanced

0.83

 clarification

0.82

 insight

0.82

 frequent

0.81

Activations Density 0.052%

links or invitations for more information or content

phrases that refer to additional information or resources

No Comments

No Known Activations