INDEX

Explanations

words related to names or identities

oai_token-act-pair · gpt-3.5-turbo

proper nouns and references to specific individuals or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UM

-1.03

Gim

-0.86

Bah

-0.86

 Force

-0.86

 Freem

-0.85

 Spac

-0.85

 Kali

-0.83

 Masonic

-0.83

Bah

-0.83

 ultr

-0.81

POSITIVE LOGITS

Barn

1.32

 Barn

1.20

Cox

1.06

 barn

1.05

ox

1.03

Roberts

1.02

 Robertson

0.99

ORN

0.98

 Jenkins

0.98

ript

0.97

Activations Density 0.462%

words related to names or identities

proper nouns and references to specific individuals or entities

No Comments

No Known Activations