INDEX

Explanations

references to military officials or military positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RegressionTest

-0.63

Autoritní

-0.59

PerformLayout

-0.55

BASELINE

-0.53

 createState

-0.52

ęło

-0.49

الحياه

-0.48

tagHelperRunner

-0.46

űr

-0.46

帖最后由

-0.46

POSITIVE LOGITS

 Generals

0.90

 generals

0.89

General

0.87

 General

0.84

general

0.83

 GENERAL

0.77

 general

0.76

GENERAL

0.73

 généraux

0.72

Gen

0.71

Activations Density 0.161%

references to military officials or military positions

No Comments

No Known Activations