INDEX

Explanations

elements related to coding, particularly those involved in device and hardware specifications or settings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

EndContext

-0.70

++]=

-0.64

Tikang

-0.62

providedIn

-0.56

"]').

-0.52

 nahilalakip

-0.52

GeoNames

-0.50

 tens

-0.49

culum

-0.49

->___

-0.49

POSITIVE LOGITS

 становника

0.78

 itſelf

0.69

makeConstraints

0.69

 resourceCulture

0.65

 myſelf

0.58

 uſed

0.57

IntoConstraints

0.57

ViewFeatures

0.57

 XNUMX

0.57

 TextAppearance

0.57

Activations Density 0.256%

elements related to coding, particularly those involved in device and hardware specifications or settings

No Comments

No Known Activations