INDEX

Explanations

programming and coding elements, particularly related to data structures and UI components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Fay

-0.57

ben

-0.56

equ

-0.55

ccione

-0.52

 dire

-0.51

 shut

-0.51

vi

-0.50

pre

-0.49

 المعيارى

-0.49

 equal

-0.48

POSITIVE LOGITS

RegressionTest

0.88

ThroughAttribute

0.87

 nemici

0.87

NUMX

0.81

WireFormat

0.81

 myſelf

0.80

rawDesc

0.78

 löytyy

0.74

 ffilmiau

0.74

 commerciali

0.72

Activations Density 0.654%

programming and coding elements, particularly related to data structures and UI components

No Comments

No Known Activations