INDEX

Explanations

questions and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Handlung

-0.62

 aidant

-0.59

 parcheggio

-0.56

ientôt

-0.56

Kontrola

-0.53

Conclusie

-0.53

 textStatus

-0.52

 résister

-0.51

 évo

-0.51

 parkir

-0.51

POSITIVE LOGITS

 &___

0.62

 referenties

0.62

TagMode

0.60

ClientSize

0.59

 ujednoznacz

0.57

msgTypes

0.55

RoutingModule

0.55

ugi

0.55

dem

0.53

ANTLR

0.53

Activations Density 0.266%

questions and inquiries

No Comments

No Known Activations