INDEX

Explanations

numerical patterns or structured data

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

PrototypeOf

-0.62

InitVars

-0.59

rull

-0.54

Rüyada

-0.53

 subcutaneous

-0.52

StructEnd

-0.52

 fondament

-0.51

 little

-0.51

 bisiklet

-0.51

cencia

-0.50

POSITIVE LOGITS

tagHelperRunner

0.66

MENAFN

0.60

featureID

0.56

FieldBuilder

0.53

 Ante

0.53

 comuniques

0.53

(°

0.51

RRect

0.47

createComponent

0.46

ContentAsync

0.46

Activations Density 0.104%

numerical patterns or structured data

No Comments

No Known Activations