INDEX

Explanations

references to technical specifications or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 BorderRadius

-0.66

ItemBackground

-0.65

TypedDataSet

-0.59

abestanden

-0.57

ValueStyle

-0.57

 siè

-0.57

Xna

-0.57

сылкі

-0.57

Sinopse

-0.55

InitVars

-0.55

POSITIVE LOGITS

Or

0.56

 kasarigan

0.54

 Chwiliwch

0.54

it

0.53

 Италијани

0.51

ConverterFactory

0.51

quo

0.50

May

0.49

Or

0.49

 فقد

0.48

Activations Density 0.731%

references to technical specifications or measurements

No Comments

No Known Activations