INDEX

Explanations

phrases or sentences enclosed by quotation marks

oai_token-act-pair · gpt-3.5-turbo

quoted speech or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

¾

-0.88

ĻĤ

-0.85

İĭ

-0.81

Ļ½

-0.80

¸

-0.80

²¾

-0.79

paren

-0.73

emis

-0.70

¥µ

-0.69

kell

-0.68

POSITIVE LOGITS

/"

0.86

sic

0.73

OTUS

0.71

["

0.67

Adds

0.65

 remark

0.64

Donnell

0.63

 justifies

0.62

Brien

0.62

into

0.60

Activations Density 0.100%

phrases or sentences enclosed by quotation marks

quoted speech or dialogue

No Comments

No Known Activations