INDEX

Explanations

References to the word "rem" or variations of it in various contexts

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

Text near "Rem" or "Cle"

np_acts-logits-general · gemini-2.0-flash

Rem, Cle, Coll prefixes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

URLException

-0.59

 виправивши

-0.56

hados

-0.54

帖最后由

-0.53

Datuak

-0.51

 通販

-0.50

nościo

-0.50

ScopeManager

-0.50

 magasiner

-0.49

/**

-0.49

POSITIVE LOGITS

ArrowToggle

0.57

enterOuterAlt

0.55

hoeddwyd

0.54

viš

0.53

Cross

0.51

enteuer

0.49

OCCURRED

0.49

 cross

0.48

 ObjectParameter

0.48

 extérieures

0.47

Activations Density 0.522%

References to the word "rem" or variations of it in various contexts

Text near "Rem" or "Cle"

Rem, Cle, Coll prefixes

No Comments

No Known Activations