INDEX

Explanations

descriptive terms related to product performance and quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

routeProvider

-0.56

setViewportView

-0.54

 متعلقه

-0.51

 Souha

-0.50

JpaRepository

-0.48

AccessorTable

-0.48

telo

-0.47

spender

-0.47

brev

-0.46

 BoxDecoration

-0.46

POSITIVE LOGITS

 construction

1.02

 appearance

0.99

 design

0.97

 looks

0.96

 build

0.95

 workmanship

0.93

 durability

0.89

 finish

0.88

 aesthetics

0.87

 craftsmanship

0.87

Activations Density 0.314%

descriptive terms related to product performance and quality

No Comments

No Known Activations