INDEX

Explanations

references to weight or density

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

 propOrder

-0.87

PMailer

-0.76

Tib

-0.70

NOPQRST

-0.69

Pranala

-0.69

HtmlAttribute

-0.67

 colspan

-0.65

Hochspringen

-0.63

RPM

-0.61

GNUC

-0.60

POSITIVE LOGITS

Heavy

1.15

 Heavy

1.14

 HEAVY

1.10

heavy

1.07

 heaviest

1.05

 heavy

0.98

 Heav

0.91

AVY

0.85

 Davy

0.85

 heavier

0.84

Activations Density 0.005%

references to weight or density

No Comments

No Known Activations