INDEX

Explanations

references to academic citations or datasets in research contexts

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

Tokens preceding numeric identifiers

np_acts-logits-general · gemini-2.0-flash

political or fight

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

BagConstraints

-0.90

الإنجليزية

-0.81

تقاوى

-0.68

 BoxDecoration

-0.66

StoreMessageInfo

-0.66

SceneManagement

-0.63

BeginInit

-0.61

 Wikimedijinoj

-0.57

Արտաքին

-0.57

 člá

-0.56

POSITIVE LOGITS

WithIOException

0.54

_();

0.51

ipient

0.48

hals

0.48

yser

0.47

nge

0.47

vka

0.47

 reste

0.47

❋

0.46

[]>

0.45

Activations Density 0.090%

references to academic citations or datasets in research contexts

Tokens preceding numeric identifiers

political or fight

No Comments

No Known Activations