INDEX

Explanations

rhetorical questions ending with the word "right."

oai_token-act-pair · gpt-3.5-turbo

rhetorical questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rament

-0.79

 lobster

-0.65

bath

-0.65

versive

-0.64

 councils

-0.63

 wheelchair

-0.63

 marsh

-0.62

 wrench

-0.62

 colon

-0.62

 mast

-0.62

POSITIVE LOGITS

 Nope

1.09

 Wrong

1.09

 Well

0.97

 Anyway

0.97

 Especially

0.95

 Wouldn

0.94

 Yeah

0.92

 Besides

0.88

Isn

0.87

 Maybe

0.87

Activations Density 0.060%

rhetorical questions ending with the word "right."

rhetorical questions

No Comments

No Known Activations