INDEX

Explanations

references to individuals and their professional roles or identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RenderAtEndOf

-0.61

GeneratedCode

-0.60

oredCriteria

-0.59

IVEREF

-0.58

 ويكيپيديا

-0.57

 فريبيس

-0.55

Santis

-0.54

ItemBackground

-0.54

RectangleBorder

-0.51

 avulla

-0.51

POSITIVE LOGITS

بوابة

0.78

AppMethodBeat

0.65

Jeografia

0.60

GeneratedValue

0.56

Atsauces

0.55

>>=

0.54

FromArgb

0.54

 onCreateView

0.54

RunWith

0.54

0.52

Activations Density 0.302%

references to individuals and their professional roles or identities

No Comments

No Known Activations