INDEX

Explanations

phrases related to legislative actions or bills

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in" used throughout the text

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

 utilized

-0.76

 coloring

-0.74

CHA

-0.74

Hispanic

-0.74

 viol

-0.72

 thru

-0.70

 canceled

-0.70

 supra

-0.70

omo

-0.70

Reviewer

-0.70

POSITIVE LOGITS

 Edinburgh

1.46

 Scotland

1.44

 Yorkshire

1.38

 Cardiff

1.36

 Wales

1.36

 Newcastle

1.35

 Glasgow

1.33

 London

1.33

 Britain

1.32

 Lanc

1.31

Activations Density 0.233%

phrases related to legislative actions or bills

instances of the word "in" used throughout the text

No Comments

No Known Activations