INDEX

Explanations

proper nouns related to the name "Angel"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Angel" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ãģ¦

-0.88

yip

-0.86

merce

-0.82

ĸļ

-0.82

theless

-0.76

perature

-0.75

ĵĺ

-0.74

 elig

-0.74

olicy

-0.74

sonian

-0.73

POSITIVE LOGITS

enos

1.10

Angel

0.98

eno

0.98

 Angel

0.95

angel

0.94

inian

0.85

 Gabriel

0.84

 Wings

0.82

 Angels

0.81

Jol

0.79

Activations Density 0.012%

proper nouns related to the name "Angel"

references to the name "Angel" in various contexts

No Known Activations