INDEX

Explanations

questions or instances of doubt in statements or situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "question" and its variations

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

rites

-0.86

pite

-0.75

Torrent

-0.74

acements

-0.67

catentry

-0.66

ãĥł

-0.66

ãĥ¼ãĥĨãĤ£

-0.65

\/\/

-0.65

chn

-0.65

 earthqu

-0.64

POSITIVE LOGITS

 whether

1.57

why

1.23

whether

1.19

 legality

1.17

 assumptions

1.06

 motives

1.06

how

0.97

 validity

0.96

 propri

0.95

 legitimacy

0.94

Activations Density 0.096%

questions or instances of doubt in statements or situations

instances of the word "question" and its variations

No Comments

No Known Activations