INDEX

Explanations

proper nouns, specifically names and titles

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dele

-0.73

Ud

-0.71

 Stewart

-0.71

Rudi

-0.69

Imp

-0.68

Dele

-0.68

Stewart

-0.67

glieder

-0.66

Gir

-0.65

 Schloss

-0.65

POSITIVE LOGITS

 Raiders

1.27

 Raider

1.20

 raider

1.20

 Raim

1.20

 raiders

1.18

Radians

1.15

RA

1.12

 RAID

1.12

Efq

1.10

 radians

1.09

Activations Density 0.065%

proper nouns, specifically names and titles

No Comments

No Known Activations

proper nouns, specifically names and titles

No Comments

No Known Activations