INDEX

Explanations

references to feedback

oai_token-act-pair · gpt-3.5-turbo

references to user feedback and its importance

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

wikipedia

-0.79

neys

-0.73

chin

-0.70

annis

-0.68

amina

-0.66

Dial

-0.65

ffe

-0.64

 Noct

-0.63

adem

-0.63

bold

-0.59

POSITIVE LOGITS

 loops

1.14

 feedback

1.09

 Feedback

1.01

 loop

0.98

0.80

 testers

0.75

 sessions

0.74

 assurance

0.74

 booths

0.73

 constructive

0.72

Activations Density 0.035%

references to feedback

references to user feedback and its importance

No Comments

No Known Activations