INDEX

Explanations

locations or proper nouns starting with the letter 'U'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "U" 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

 Noir

-0.66

 Codex

-0.65

CMS

-0.63

 Authority

-0.61

 Perse

-0.61

 practicable

-0.61

 separated

-0.60

 bars

-0.59

 specialization

-0.59

 electronic

-0.58

POSITIVE LOGITS

prising

1.34

nexpected

1.31

lyss

1.27

topia

1.26

seless

1.24

PDATED

1.22

gly

1.20

pperc

1.17

mber

1.16

rolog

1.09

Activations Density 0.049%

locations or proper nouns starting with the letter 'U'

occurrences of the letter "U" in various contexts

No Comments

No Known Activations