INDEX

Explanations

questions or statements that begin with "is it" or "it is."

oai_token-act-pair · gpt-3.5-turbo

questions that begin with "Is it" and are reflective in nature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

former

-0.80

escription

-0.73

dit

-0.72

bies

-0.72

umbn

-0.70

details

-0.70

acas

-0.69

è¦ļéĨĴ

-0.69

umber

-0.68

papers

-0.67

POSITIVE LOGITS

 really

1.12

 ever

1.08

1.00

 REALLY

0.99

 Really

0.96

?'

0.95

 alright

0.95

 conceivable

0.93

?:

0.93

...?

0.92

Activations Density 0.101%

questions or statements that begin with "is it" or "it is."

questions that begin with "Is it" and are reflective in nature

No Comments

No Known Activations