INDEX

Explanations

phrases containing the word "Be"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Be" or variations thereof

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 glide

-0.66

 Ples

-0.66

 residue

-0.65

 orbit

-0.64

 pole

-0.63

 drift

-0.62

 hoops

-0.61

 portrait

-0.61

 mash

-0.60

 excise

-0.60

POSITIVE LOGITS

hemoth

1.35

yond

1.27

arers

1.23

ijing

1.22

arer

1.20

acons

1.12

arded

1.11

zos

1.09

heading

1.08

aum

1.06

Activations Density 0.030%

phrases containing the word "Be"

mentions of the word "Be" or variations thereof

No Comments

No Known Activations