INDEX

Explanations

expressions indicating frequency or occurrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 throughout

-0.75

throughout

-0.70

 Throughout

-0.68

Throughout

-0.66

 THRO

-0.66

PageFactory

-0.44

碎

-0.44

 Numerade

-0.44

 Taktlose

-0.43

 combineReducers

-0.42

POSITIVE LOGITS

OGND

0.77

Portale

0.72

SBATCH

0.69

InitVars

0.67

Diwedd

0.67

 الرياضيه

0.66

 Roskov

0.66

="@+

0.66

脚注の使い方

0.66

IndentedString

0.65

Activations Density 0.114%

expressions indicating frequency or occurrence

No Comments

No Known Activations