INDEX

Explanations

mentions of specific names or terms, potentially related to celebrities or public figures

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names associated with individuals or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Radiant

-1.01

 Rend

-0.98

Tid

-0.96

 Trin

-0.90

Tud

-0.90

 Nost

-0.89

NT

-0.88

 Timbers

-0.86

Rat

-0.84

Nit

-0.83

POSITIVE LOGITS

au

1.30

aul

1.14

Lau

1.03

Marie

0.97

HEL

0.94

Kau

0.93

 Kaufman

0.93

Mau

0.92

aus

0.90

AU

0.90

Activations Density 0.603%

mentions of specific names or terms, potentially related to celebrities or public figures

proper nouns and names associated with individuals or characters

No Comments

No Known Activations