INDEX

Explanations

proper nouns likely related to different entities or individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and brands

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

nels

-0.73

illed

-0.69

âĶģ

-0.69

illing

-0.69

-----------

-0.67

Pwr

-0.66

ilities

-0.65

Ĥª

-0.65

ulate

-0.64

ÄŁ

-0.64

POSITIVE LOGITS

oyd

1.11

ongevity

0.96

ibrary

0.95

ounge

0.89

yrics

0.88

 Luthor

0.85

utenant

0.84

uggage

0.84

uminati

0.79

ipop

0.79

Activations Density 0.181%

proper nouns likely related to different entities or individuals

proper nouns, specifically names and brands

No Comments

No Known Activations