INDEX

Explanations

mathematical symbols and structure related to theorems and proofs

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

Mathematical environments: aligned

np_acts-logits-general · gemini-2.0-flash

LaTeX aligned environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 محفوظة

-0.45

tagHelperRunner

-0.42

setArguments

-0.37

ensaft

-0.34

bes

-0.32

unsch

-0.32

 пусть

-0.32

tissimi

-0.32

Ча

-0.31

 häufiger

-0.31

POSITIVE LOGITS

 dezelve

0.59

 <<<<<<<<<<<<<<

0.54

 kasarigan

0.54

---*/

0.52

featureID

0.52

 BrowserModule

0.50

 pleaſure

0.48

 ſind

0.47

 ainfi

0.47

RTGC

0.47

Activations Density 0.500%

mathematical symbols and structure related to theorems and proofs

Mathematical environments: aligned

LaTeX aligned environments

No Comments

No Known Activations