INDEX

Explanations

phrases related to warning or advice

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their usage in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

olitical

-0.81

Political

-0.80

uties

-0.74

OND

-0.73

lihood

-0.73

cius

-0.71

onym

-0.71

Roaming

-0.70

arial

-0.70

ourses

-0.70

POSITIVE LOGITS

 haha

0.91

oh

0.81

 somew

0.78

 suffice

0.72

wow

0.72

 congr

0.72

 grinning

0.70

 thankfully

0.70

eh

0.70

 Genie

0.70

Activations Density 0.552%

phrases related to warning or advice

punctuation marks and their usage in sentences

No Comments

No Known Activations