INDEX

Explanations

numerical values and their contexts

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

Follows punctuation or formatting marks

np_acts-logits-general · gemini-2.0-flash

code snippets and technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.69

styleType

-0.68

 الرياضيه

-0.67

argout

-0.67

featureID

-0.66

IsContent

-0.65

TypedDataSet

-0.65

/***/

-0.64

TagHelper

-0.62

FormTagHelper

-0.62

POSITIVE LOGITS

0.54

 HasFactory

0.50

0.46

 चीज़ों

0.46

fahren

0.46

 AppColors

0.44

 sanoo

0.44

Consensus

0.44

ướt

0.44

Activations Density 0.092%

numerical values and their contexts

Follows punctuation or formatting marks

code snippets and technical terms

No Comments

No Known Activations