INDEX

Explanations

references to types of elements or components in various contexts

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

 GenerationType

-0.86

sizeCache

-0.76

 doInBackground

-0.75

lihood

-0.74

 vacacionales

-0.69

DispatchToProps

-0.69

 Audiodateien

-0.69

 AppBar

-0.68

shadowRadius

-0.66

Amicalement

-0.66

POSITIVE LOGITS

 elements

0.76

hasMoreElements

0.73

 元素

0.73

 Elements

0.72

Elements

0.72

elements

0.69

 Elemente

0.63

IElement

0.62

ناصر

0.62

 getElement

0.61

Activations Density 0.072%

references to types of elements or components in various contexts

No Comments

No Known Activations