INDEX

Explanations

references to various plotting and graphing functions or types within a programming or data visualization context

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

VideoCapture

-0.62

addPreferredGap

-0.54

 Dede

-0.53

 chante

-0.53

ligere

-0.52

 viti

-0.51

zep

-0.51

'{{

-0.51

jerne

-0.51

amine

-0.51

POSITIVE LOGITS

 ExecuteAsync

0.85

SharedCtor

0.85

tagext

0.76

 createState

0.68

 plots

0.65

chartInstance

0.64

ieteur

0.63

 Diagram

0.62

 Plots

0.62

ViewFeatures

0.61

Activations Density 0.208%

references to various plotting and graphing functions or types within a programming or data visualization context

No Comments

No Known Activations