INDEX

Explanations

technical terms and concepts related to research methodologies and data analysis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elman

-0.51

Хьажоргаш

-0.48

ASX

-0.47

таратура

-0.45

 composite

-0.41

 Praxis

-0.40

 nahilalakip

-0.39

Readings

-0.39

 final

-0.39

POSITIVE LOGITS

 تضيفلها

0.75

 accordingly

0.74

tagHelperRunner

0.73

 conséquence

0.73

 thereupon

0.71

MigrationBuilder

0.71

)";

0.70

 correspondingly

0.68

)");

0.66

+:+

0.65

Activations Density 1.257%

technical terms and concepts related to research methodologies and data analysis

No Comments

No Known Activations