INDEX

Explanations

proper nouns, specifically names of people

oai_token-act-pair · gpt-4-turbo

the word "Jude"

oai_token-act-pair · gpt-3.5-turbo

references to specific names or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

AST

-0.67

eur

-0.67

ories

-0.65

olesterol

-0.64

Hol

-0.62

eria

-0.62

 Shipping

-0.61

ben

-0.60

 star

-0.57

 stars

-0.57

POSITIVE LOGITS

successfully

0.71

wagon

0.70

WIND

0.69

veyard

0.69

animous

0.68

emale

0.68

vae

0.66

lace

0.65

forth

0.65

sets

0.64

Activations Density 0.000%

proper nouns, specifically names of people

the word "Jude"

references to specific names or proper nouns

No Comments

No Known Activations