INDEX

Explanations

phrases or quotes ending with a specific punctuation mark (",")

oai_token-act-pair · gpt-3.5-turbo

instances of spoken dialogue or quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

²¾

-0.83

İĭ

-0.81

eds

-0.70

Ĭ

-0.67

 unequ

-0.66

rats

-0.65

§

-0.64

ailing

-0.63

²

-0.62

eb

-0.62

POSITIVE LOGITS

 reads

0.83

,'"

0.73

 says

0.72

?'"

0.69

!'"

0.69

 Hurricanes

0.68

 recalls

0.66

 Warm

0.66

',"

0.63

said

0.63

Activations Density 0.094%

phrases or quotes ending with a specific punctuation mark (",")

instances of spoken dialogue or quotations

No Comments

No Known Activations