INDEX

Explanations

terms related to necessity and importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

 EdgeInsets

-0.62

 regler

-0.52

Regi

-0.50

 durumda

-0.50

 vulgaires

-0.49

 aufnehmen

-0.48

স্ত

-0.47

 frumos

-0.46

 laws

-0.46

GOTREF

-0.45

POSITIVE LOGITS

NUMX

0.76

InputBorder

0.76

enumi

0.71

存于互联网档案馆

0.69

argout

0.67

 feature

0.66

 hallmark

0.65

 مشين

0.65

 highlight

0.61

 invokingState

0.59

Activations Density 0.383%

terms related to necessity and importance

No Comments

No Known Activations