INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names, particularly those related to individuals or organizations

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

OLOGY

-0.76

ACTED

-0.76

advertisement

-0.68

 institutional

-0.65

 systematic

-0.64

achusetts

-0.64

itutional

-0.64

eanor

-0.64

OLOG

-0.64

ocrats

-0.63

POSITIVE LOGITS

Kur

1.22

istani

1.07

ernel

1.00

thur

0.93

assic

0.90

rier

0.88

geon

0.87

Zar

0.85

immune

0.84

ihara

0.83

Activations Density 0.005%

proper nouns related to individuals

proper nouns or names, particularly those related to individuals or organizations

No Comments

No Known Activations