INDEX

Explanations

mathematical expressions and calculations involving variables and operations

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

mathematical expressions and numbers

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

statements that compare or evaluate relationships—especially mathematical comparison/simplification prompts and assessments of compatibility.

oai_token-act-pair · gpt-5 Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 CreateTagHelper

-0.93

 سكانية

-0.73

Tembelea

-0.67

 виправивши

-0.66

expandindo

-0.66

GEBURTSDATUM

-0.65

 Infórmanos

-0.65

 autorytatywna

-0.65

UnusedPrivate

-0.63

awtextra

-0.62

POSITIVE LOGITS

 compañ

0.33

 متحده

0.33

 للاسماء

0.29

 tibur

0.28

 Stirn

0.27

 Früh

0.27

Rohy

0.27



0.27

CFLAGS

0.26

 capucha

0.25

Activations Density 14.662%

mathematical expressions and calculations involving variables and operations

mathematical expressions and numbers

statements that compare or evaluate relationships—especially mathematical comparison/simplification prompts and assessments of compatibility.

No Comments

No Known Activations