INDEX

Explanations

references to military actions and locations, particularly in relation to Afghanistan and Iraq

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

newswire

-0.57

 acorns

-0.55

Kaieteur

-0.54

 Corinth

-0.53

참고

-0.53

ixeira

-0.52

 москве

-0.52

etragen

-0.51

 Alois

-0.51

 Sinh

-0.51

POSITIVE LOGITS

 BoxFit

0.69

 iprot

0.69

 Италијани

0.66

LookAnd

0.65

StoryboardSegue

0.64

yntaxException

0.62

 ComVisible

0.54

 оригіналу

0.53

 honeymoon

0.52

 кӀ

0.51

Activations Density 0.438%

references to military actions and locations, particularly in relation to Afghanistan and Iraq

No Comments

No Known Activations