INDEX

Explanations

references to specific names and terms associated with cultural or regional contexts

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

WebElementEntity

-0.77

 "..\..\..\

-0.75

webElementXpaths

-0.74

SequentialGroup

-0.73

 "..\..\

-0.69

WebVitals

-0.67

 Exacts

-0.64

IntoConstraints

-0.64

 BitmapFactory

-0.63

fjspx

-0.63

POSITIVE LOGITS

eng

0.61

ongs

0.57

ux

0.56

ang

0.52

OGND

0.49

ENG

0.48

 durs

0.48

ings

0.47

ong

0.47

agrad

0.46

Activations Density 0.184%

references to specific names and terms associated with cultural or regional contexts

No Comments

No Known Activations