INDEX

Explanations

references to military and defense-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

AddTagHelper

-0.76

الحياه

-0.74

 Roskov

-0.71

 Chwiliwch

-0.69

 lenker

-0.62

__(/*!

-0.59

 Army

-0.58

NewRow

-0.57

 AssemblyCulture

-0.57

verwijspagina

-0.57

POSITIVE LOGITS

 bases

0.54

ApiModelProperty

0.54

 academies

0.53

 Bases

0.51

 installations

0.51

 academy

0.50

 Academy

0.50

 Atta

0.49

 Wives

0.49

Controllo

0.48

Activations Density 0.272%

references to military and defense-related terms

No Comments

No Known Activations