INDEX

Explanations

proper names

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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

-0.73

 ANGEL

-0.72

Sof

-0.69

 Pradesh

-0.67

 Petra

-0.66

ãĥŁ

-0.65

 Haram

-0.62

 Heavenly

-0.62

 Sasha

-0.62

Nusra

-0.60

POSITIVE LOGITS

enstein

1.13

nick

1.13

inger

1.10

enberg

1.09

quist

1.09

ansky

1.09

zinski

1.08

anson

1.06

inski

1.06

insky

1.05

Activations Density 0.247%

proper names

proper nouns, specifically names of people

No Comments

No Known Activations