INDEX

Explanations

first-person statements expressing awareness or ability in a specific context

oai_token-act-pair · gpt-3.5-turbo

expressions of personal awareness and concern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

SIGN

-0.59

quished

-0.59

atars

-0.58

rus

-0.58

 Harvest

-0.58

VIDEO

-0.57

 Slov

-0.57

 Photograph

-0.57

ima

-0.56

————————

-0.55

POSITIVE LOGITS

 concerned

1.15

 recollection

0.79

 knowledge

0.78

 ascertain

0.77

 aware

0.77

knowledge

0.72

 know

0.69

 understanding

0.69

resp

0.67

lege

0.65

Activations Density 0.051%

first-person statements expressing awareness or ability in a specific context

expressions of personal awareness and concern

No Comments

No Known Activations