INDEX

Explanations

prepositions 'in' followed by a location or physical description

oai_token-act-pair · gpt-3.5-turbo

the presence of the phrase "in" used repeatedly 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

inion

-0.71

ente

-0.68

itual

-0.65

otide

-0.65

hler

-0.64

sett

-0.64

Ĥİ

-0.63

ZA

-0.61

onics

-0.61

obe

-0.61

POSITIVE LOGITS

 action

1.33

action

1.07

 silhouette

1.02

 pictures

0.99

 screenshots

0.95

actions

0.95

 theaters

0.95

 photographs

0.93

 Action

0.88

 afar

0.88

Activations Density 0.155%

prepositions 'in' followed by a location or physical description

the presence of the phrase "in" used repeatedly in various contexts

No Comments

No Known Activations