INDEX

Explanations

proper nouns and important terminology related to various topics

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

Tokens followed by "Q:" or "Kenosha"

np_acts-logits-general · gemini-2.0-flash

PRRSV or Kenosha

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

KELEY

-0.57

didSet

-0.56

München

-0.56

sizeCache

-0.55

 вида

-0.55

/$',

-0.55

mässig

-0.55

 Webseiten

-0.55

-0.54

Bordeaux

-0.54

POSITIVE LOGITS

RenderAtEndOf

0.69

MethodImpl

0.67

ſelves

0.66

 AppColors

0.64

 समीक्षक

0.63

 FontWeight

0.62

 iſt

0.62

 CURLOPT

0.61

ſelf

0.60

\<^

0.60

Activations Density 0.791%

proper nouns and important terminology related to various topics

Tokens followed by "Q:" or "Kenosha"

PRRSV or Kenosha

No Comments

No Known Activations