INDEX

Explanations

words related to names, specifically "Ari" with various spellings

oai_token-act-pair · gpt-3.5-turbo

the name "Jabari" or its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mable

-0.74

cussion

-0.73

ertodd

-0.72

conscious

-0.72

hops

-0.70

filled

-0.70

pages

-0.69

 PRESIDENT

-0.69

MFT

-0.66

é¾įå¥ĳå£«

-0.64

POSITIVE LOGITS

ari

0.92

ya

0.90

asing

0.87

zon

0.86

Äĩ

0.86

asis

0.86

ason

0.83

yah

0.82

aga

0.82

ensis

0.81

Activations Density 0.008%

words related to names, specifically "Ari" with various spellings

the name "Jabari" or its variations

No Comments

No Known Activations