INDEX

Explanations

code segments that indicate logical structures or functions within programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

etron

-0.49

 Dolan

-0.48

haviors

-0.48

strö

-0.47

te

-0.46

 FEES

-0.44

Auszeichnungen

-0.44

qu

-0.43

aclk

-0.43

 fees

-0.43

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.88

 Réponses

0.82

 للاسماء

0.82

0.79



0.76

 الحره

0.75

WebVitals

0.74

رشف

0.74

Hentet

0.74

Activations Density 0.084%

code segments that indicate logical structures or functions within programming syntax

No Comments

No Known Activations