INDEX

Explanations

occurrences of the word "this" and various forms of the letter "m."

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

"this" followed by a period or variable assignment

np_acts-logits-general · gemini-2.0-flash

this. followed by identifier

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ogóle

-0.72

sslich

-0.50

 كورة

-0.50

scribers

-0.50

 leçons

-0.49

 ivelany

-0.49

 behövs

-0.49

 তারিখ

-0.48

jmniej

-0.47

expiresIn

-0.47

POSITIVE LOGITS

0.73

 resourceCulture

0.67

TypedDataSet

0.65

 surla

0.62

 виправивши

0.61

ModelAdmin

0.59

 насељу

0.59

มาะ

0.57

awtextra

0.56

abestanden

0.55

Activations Density 0.008%

occurrences of the word "this" and various forms of the letter "m."

"this" followed by a period or variable assignment

this. followed by identifier

No Comments

No Known Activations