INDEX

Explanations

numeric values or measurements typically associated with experimental results

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

 Maura

-0.76

($"

-0.68

 Reagents

-0.67

zey

-0.66

 Essay

-0.63

 Rhetoric

-0.63

 Lopes

-0.63

chose

-0.63

Filmografie

-0.62

Hov

-0.62

POSITIVE LOGITS

±

0.85

ConstraintMaker

0.84

StructEnd

0.79

 فريبيس

0.78

eventbus

0.78

 OnInit

0.70

TabIndex

0.68

complexContent

0.67

ViewFeatures

0.67

 חיצוניים

0.66

Activations Density 0.006%

numeric values or measurements typically associated with experimental results

No Comments

No Known Activations