INDEX

Explanations

numerical representations or symbols related to data and statistics

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

Numbers within square brackets

np_acts-logits-general · gemini-2.0-flash

numbers and citations

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

WORKS

-0.53

 décé

-0.52

dreaming

-0.50

ACHEL

-0.48

alion

-0.47

BarChart

-0.47

urismo

-0.47

 teaching

-0.46

sog

-0.46

 Cassini

-0.46

POSITIVE LOGITS

InitVars

0.76

parsedMessage

0.72

 estekak

0.63

TagMode

0.61

SerializedSize

0.60

LookAnd

0.60

ISupport

0.55

 iVar

0.54

 consultato

0.53

 addSubview

0.53

Activations Density 0.296%

numerical representations or symbols related to data and statistics

Numbers within square brackets

numbers and citations

No Comments

No Known Activations