INDEX

Explanations

references to system file paths, specifically focusing on the word "root"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "root" and related terms 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

odies

-0.69

 corps

-0.66

 sinks

-0.65

ickr

-0.64

insula

-0.64

 captcha

-0.62

 dysph

-0.62

 hypnot

-0.62

agall

-0.61

 hemor

-0.60

POSITIVE LOGITS

root

1.25

roots

1.25

bush

1.03

é¾

0.92

 Roots

0.88

pring

0.84

Root

0.84

ourcing

0.80

origin

0.79

0.78

Activations Density 0.005%

references to system file paths, specifically focusing on the word "root"

variations of the word "root" and related terms in various contexts

No Comments

No Known Activations