INDEX

Explanations

code statements that manipulate arrays or data structures

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

pen

-0.42

bukkit

-0.41

 Zusch

-0.41

hasRole

-0.40

jface

-0.39

PEN

-0.38

mis

-0.37

줍

-0.37

 Durch

-0.37

POSITIVE LOGITS

 مشين

0.85

Tikang

0.84

 estimés

0.83

 snippetHide

0.82

findpost

0.82

 Dage

0.74

 ostavi

0.74

 otomatig

0.71

 testSet

0.70

Aholisi

0.68

Activations Density 0.374%

code statements that manipulate arrays or data structures

No Comments

No Known Activations