INDEX

Explanations

specific locations and actions related to travel or exploration

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

 concerne

-0.41

 esetén

-0.41

 prévention

-0.41

 notizia

-0.40

왔

-0.40

ילות

-0.39

 obsahuje

-0.39

 grans

-0.39

psc

-0.38

 popolare

-0.37

POSITIVE LOGITS

 Meksiku

0.93

 HasFactory

0.86

AccessorTable

0.79

oredCriteria

0.76

 BoxFit

0.73

abestanden

0.72

íncia

0.71

 themſelves

0.70

 disambiguazione

0.70

 <=",

0.69

Activations Density 0.168%

specific locations and actions related to travel or exploration

No Comments

No Known Activations