INDEX

Explanations

text that directs the reader to 'Read more'

oai_token-act-pair · gpt-3.5-turbo

ellipses and repeated symbols that indicate omitted text or continuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

oche

-0.71

thora

-0.71

alion

-0.70

ially

-0.67

ifully

-0.66

 permitting

-0.66

hematically

-0.65

ratulations

-0.65

æĪ¦

-0.65

 spar

-0.64

POSITIVE LOGITS

 Appears

0.96

 Continue

0.83

 READ

0.80

 âĢİ

0.77

 Free

0.75

 Author

0.75

 Read

0.73

 Bride

0.69

 TRANS

0.69

 INTER

0.67

Activations Density 0.065%

text that directs the reader to 'Read more'

ellipses and repeated symbols that indicate omitted text or continuation

No Comments

No Known Activations