INDEX

Explanations

proper nouns, specifically names of people

oai_token-act-pair · gpt-3.5-turbo

references to advertisements and specific names related to individuals and demographics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rent

-0.91

ulously

-0.75

tering

-0.71

chem

-0.69

medi

-0.68

 Palest

-0.68

plets

-0.66

de

-0.65

rely

-0.64

 Hebdo

-0.64

POSITIVE LOGITS

Jenn

0.98

acebook

0.87

advertisement

0.87

manship

0.84

maxwell

0.84

ipedia

0.78

 Jenn

0.77

sburgh

0.75

isode

0.74

imity

0.74

Activations Density 0.025%

proper nouns, specifically names of people

references to advertisements and specific names related to individuals and demographics

No Comments

No Known Activations