INDEX

Explanations

numerical values or metrics related to performance or characteristics in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Roskov

-0.84

 ModelExpression

-0.73

Hozzáférés

-0.64



-0.62

GraphicsUnit

-0.60

 SafeMath

-0.59

epam

-0.58

tagext

-0.58

urlpatterns

-0.57

featureID

-0.57

POSITIVE LOGITS

console

0.90

 console

0.83

const

0.72

 const

0.72

let

0.61

let

0.60

setTimeout

0.57

debugger

0.54

InjectAttribute

0.50

ways

0.49

Activations Density 0.040%

numerical values or metrics related to performance or characteristics in a dataset

No Comments

No Known Activations