INDEX

Explanations

phrases indicating something is subject to change

oai_token-act-pair · gpt-3.5-turbo

terms and phrases indicating conditions or subjects that are subject to change

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

miah

-0.79

oled

-0.72

ppa

-0.71

 Started

-0.70

john

-0.69

anted

-0.69

emen

-0.68

arte

-0.68

ynes

-0.66

Tool

-0.66

POSITIVE LOGITS

 scrutiny

1.21

 periodic

1.06

 rigorous

0.99

 ridicule

0.98

 modification

0.96

 stringent

0.95

 fluctuations

0.95

 cancellation

0.94

 criticism

0.91

 stricter

0.90

Activations Density 0.072%

phrases indicating something is subject to change

terms and phrases indicating conditions or subjects that are subject to change

No Comments

No Known Activations