INDEX

Explanations

terms related to syndicated content or media distribution

oai_token-act-pair · gpt-3.5-turbo

words related to syndication and organized groups

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

 Ness

-0.77

FUL

-0.72

 Anita

-0.67

 Colo

-0.66

 pengu

-0.65

 Miko

-0.64

 prick

-0.61

 Palace

-0.61

ghazi

-0.60

 stout

-0.60

POSITIVE LOGITS

icate

1.77

ication

1.69

icated

1.68

icates

1.57

icator

1.52

icating

1.41

icators

1.36

ications

1.32

uction

1.21

esm

1.19

Activations Density 0.028%

terms related to syndicated content or media distribution

words related to syndication and organized groups

No Comments

No Known Activations