INDEX

Explanations

phrases or descriptions related to unknown or unidentified entities

oai_token-act-pair · gpt-3.5-turbo

references to unidentified entities or individuals 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

owder

-0.84

ushima

-0.84

utic

-0.80

bourg

-0.79

acket

-0.79

neys

-0.74

boa

-0.72

apers

-0.71

©¶æ

-0.71

byss

-0.71

POSITIVE LOGITS

 assailants

1.01

 quantity

1.00

 assailant

0.93

 origin

0.80

ities

0.79

 quantities

0.76

 number

0.75

 Mortal

0.75

 amount

0.75

 circumstances

0.74

Activations Density 0.068%

phrases or descriptions related to unknown or unidentified entities

references to unidentified entities or individuals in various contexts

No Comments

No Known Activations