INDEX

Explanations

proper nouns, specifically names of individuals

oai_token-act-pair · gpt-3.5-turbo

references to the name "Don" and its various forms or related phrases

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

Negative Logits

ilogy

-0.74

 permissible

-0.71

andowski

-0.69

paio

-0.65

ERROR

-0.60

properties

-0.59

onductor

-0.59

icol

-0.58

»Ĵ

-0.58

ãĥķãĤ©

-0.57

POSITIVE LOGITS

brook

0.73

ibles

0.73

cha

0.70

 Cheong

0.67

ue

0.65

hips

0.65

Jr

0.63

Yen

0.63

combe

0.60

ude

0.60

Activations Density 0.109%

proper nouns, specifically names of individuals

references to the name "Don" and its various forms or related phrases

No Known Activations