INDEX

Explanations

sentences related to conflicts, protests, government actions, and political events

oai_token-act-pair · gpt-3.5-turbo

punctuation marks at the end of sentences

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

 dime

-0.88

 glim

-0.87

 tornado

-0.85

 pudding

-0.78

 tremend

-0.77

 pancakes

-0.77

nesota

-0.75

 jugg

-0.75

 brainstorm

-0.75

 darn

-0.74

POSITIVE LOGITS

 Officials

1.29

 Authorities

1.29

 Dozens

1.25

 Meanwhile

1.22

 Experts

1.22

 Protesters

1.21

 Thousands

1.21

 Hundreds

1.18

 According

1.18

 However

1.17

Activations Density 0.301%

sentences related to conflicts, protests, government actions, and political events

punctuation marks at the end of sentences

No Comments

No Known Activations