INDEX

Explanations

architectural features and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

évaluateur

-0.57

EndInit

-0.56

czną

-0.56

 NSCoder

-0.51

GOTREF

-0.51

 معد

-0.51

MenuGroup

-0.51

 whis

-0.51

orghini

-0.50

apunov

-0.49

POSITIVE LOGITS

intios

0.57

 originais

0.55

 Ionic

0.55

 capitals

0.54

 niches

0.54

 oeil

0.54

 arched

0.53

 arches

0.53

 flanking

0.53

diensten

0.52

Activations Density 0.111%

architectural features and descriptions

No Comments

No Known Activations