INDEX

Explanations

acronyms and technical terms

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific brands or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

blogs

-0.56

iris

-0.56

enhagen

-0.55

responsible

-0.55

kar

-0.53

 Hearth

-0.53

liest

-0.52

 Originally

-0.52

 Kimmel

-0.51

letters

-0.50

POSITIVE LOGITS

ebted

0.63

jri

0.63

 moniker

0.63

 conco

0.61

 workforce

0.61

 employee

0.59

 wardrobe

0.58

issance

0.58

 iteration

0.58

 celebration

0.57

Activations Density 0.948%

acronyms and technical terms

proper nouns and specific brands or entities

No Comments

No Known Activations