INDEX

Explanations

proper nouns, specifically names like "Tamir" and variations

oai_token-act-pair · gpt-3.5-turbo

the name "Tam" 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

 mileage

-0.80

 unchecked

-0.73

ģĸ

-0.70

ĺħ

-0.67

 uranium

-0.66

ĻĤ

-0.66

 tremend

-0.66

 commissions

-0.65

 anecd

-0.64

eering

-0.64

POSITIVE LOGITS

Tam

1.21

pering

1.20

pered

1.13

borgh

1.01

my

0.95

eless

0.94

iami

0.93

Ã¡s

0.93

neys

0.89

ara

0.89

Activations Density 0.007%

proper nouns, specifically names like "Tamir" and variations

the name "Tam" in various contexts

No Comments

No Known Activations