INDEX

Explanations

strings of numerical values and related identifiers, likely pertaining to items or data entries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ModelAndView

-0.55

amen

-0.53

Glo

-0.52

 bour

-0.50

unzi

-0.49

wur

-0.48

共

-0.48

hood

-0.48

यं

-0.48

pak

-0.47

POSITIVE LOGITS

 AssemblyProduct

0.64

 Mérimée

0.61

ValueStyle

0.60

Geplaatst

0.60

expandindo

0.59

ьаж

0.58

InitVars

0.58

évaluateur

0.57

Referencies

0.56

eleste

0.56

Activations Density 0.957%

strings of numerical values and related identifiers, likely pertaining to items or data entries

No Comments

No Known Activations