INDEX

Explanations

quotations introduced by the word "said"

oai_token-act-pair · gpt-3.5-turbo

instances of reported speech or quotations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ILCS

-0.84

FL

-0.76

à¦

-0.69

nig

-0.65

 afore

-0.63

)|

-0.62

 Expend

-0.60

otin

-0.60

aired

-0.59

Made

-0.59

POSITIVE LOGITS

terday

0.76

 anecd

0.75

inery

0.72

uden

0.71

pse

0.71

bara

0.67

 bluntly

0.66

htaking

0.66

etheless

0.65

enegger

0.65

Activations Density 0.213%

quotations introduced by the word "said"

instances of reported speech or quotations

No Comments

No Known Activations