INDEX

Explanations

phrases related to removing or abolishing something

oai_token-act-pair · gpt-3.5-turbo

references to the concept of removal or elimination in various contexts

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

lake

-0.81

llah

-0.75

meet

-0.74

SPONSORED

-0.73

 toget

-0.72

Ken

-0.71

strate

-0.71

Ã©e

-0.71

RI

-0.68

PLA

-0.68

POSITIVE LOGITS

 pesky

1.29

 notion

1.11

 veil

1.06

 entirety

1.05

 stigma

1.03

 possibility

1.03

 unnecessary

1.03

 troublesome

1.03

 offending

1.00

 superflu

0.98

Activations Density 0.204%

phrases related to removing or abolishing something

references to the concept of removal or elimination in various contexts

No Comments

No Known Activations