INDEX

Explanations

phrases indicating multiple instances or occurrences

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

 combination

-0.76

combination

-0.73

 combinations

-0.69

 Combination

-0.69

Combination

-0.64

 combo

-0.60

 mixture

-0.59

 combos

-0.59

 combinaison

-0.59

 kombin

-0.58

POSITIVE LOGITS

 Obrador

0.74

mybatisplus

0.72

WithIOException

0.69

IntoConstraints

0.64

apimachinery

0.63

 GenerationType

0.63

 estimés

0.63

 Commencez

0.59

 BorderRadius

0.57

principalTable

0.57

Activations Density 0.060%

phrases indicating multiple instances or occurrences

No Comments

No Known Activations