INDEX

Explanations

connections and relationships between variables or conditions

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

van

-0.52

de

-0.51

-0.48

dem

-0.48

-0.46

defineProperty

-0.45

 prior

-0.45

-0.43

ungsver

-0.43

 Persson

-0.43

POSITIVE LOGITS

 دیکھیے

0.82

########.

0.81

GEBURTSDATUM

0.78

ViewFeatures

0.78

mybatisplus

0.77

 lenker

0.76

 AssemblyCulture

0.75

 ―――――

0.71

 iprot

0.70

UnusedPrivate

0.69

Activations Density 0.343%

connections and relationships between variables or conditions

No Comments

No Known Activations