INDEX

Explanations

references to the word "Angel"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãģ¦

-0.90

sonian

-0.78

yip

-0.78

merce

-0.77

ĸļ

-0.76

perature

-0.75

ongyang

-0.74

reditary

-0.73

 elig

-0.73

¡

-0.73

POSITIVE LOGITS

enos

1.13

Angel

1.04

 Angel

1.02

eno

1.00

angel

0.96

 Gabriel

0.89

inian

0.86

 Metatron

0.86

ique

0.82

Jol

0.80

Activations Density 0.009%

references to the word "Angel"

occurrences of the word "Angel" in various contexts

No Comments

No Known Activations