INDEX

Explanations

mathematical terminology related to mapping and morphisms

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

abestanden

-0.68

AndEndTag

-0.59

Explanation

-0.53

 croce

-0.53

 dAtA

-0.53

ContextCompat

-0.52

campista

-0.51

fromCharCode

-0.51

Становништво

-0.51

 immédiatement

-0.47

POSITIVE LOGITS

 وتسجيلات

0.65

thansa

0.58

aop

0.57

ztus

0.57

0.55

 MediaType

0.54

 👎

0.53

CloseOperation

0.53

Portail

0.52

rschein

0.52

Activations Density 0.328%

mathematical terminology related to mapping and morphisms

No Comments

No Known Activations

mathematical terminology related to mapping and morphisms

No Comments

No Known Activations