INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

âĶĢâĶĢ

-0.72

 Windsor

-0.71

 Cecil

-0.68

 Brittany

-0.67

 Michigan

-0.67

 Wayne

-0.66

LEASE

-0.66

 stock

-0.65

 Mercury

-0.64

 Beacon

-0.63

POSITIVE LOGITS

hari

1.08

ibaba

1.05

oub

0.98

zynski

0.97

itars

0.96

iani

0.95

imov

0.92

awar

0.89

dh

0.89

wal

0.89

Activations Density 0.174%

names of individuals

proper nouns, specifically names of people

No Comments

No Known Activations