INDEX

Explanations

terms related to collisions, particularly in scientific or technical contexts

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

 مشين

-0.96

ьаж

-0.89

RemoveField

-0.88

StructEnd

-0.85

onomía

-0.84

adona

-0.82

shank

-0.79

ⓧ

-0.78

 ristoranti

-0.78

RetentionPolicy

-0.77

POSITIVE LOGITS

 collision

1.16

 Collision

1.07

 collisions

1.02

 Coll

0.90

 collide

0.88

collision

0.87

Collision

0.85

 collided

0.83

 colliding

0.80

Coll

0.73

Activations Density 0.003%

terms related to collisions, particularly in scientific or technical contexts

No Comments

No Known Activations