INDEX

Explanations

references to omitted or incomplete information in a context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endphp

-0.78

Parcelize

-0.70

 resourceCulture

-0.70

oredCriteria

-0.68

 AssemblyVersion

-0.67

tvguidetime

-0.66

 GenerationType

-0.63

دانشنامهٔ

-0.62

Sucesor

-0.62

 éprou

-0.62

POSITIVE LOGITS

 context

0.81

 contexto

0.75

 contextual

0.72

context

0.65

 circumstances

0.58

 Context

0.58

 контек

0.58

 Kontext

0.57

 contexte

0.56

Context

0.53

Activations Density 0.490%

references to omitted or incomplete information in a context

No Comments

No Known Activations