INDEX

Explanations

references to specific scientific terms or proper nouns

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

Tokens starting with "Lan"

np_acts-logits-general · gemini-2.0-flash

Lan as a prefix

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

andum

-0.61

JAMIN

-0.61

nolia

-0.60

 ***/

-0.60

 purpoſe

-0.60

onViewCreated

-0.60

źć

-0.59

Portale

-0.58

 Italijani

-0.58

VersionUID

-0.58

POSITIVE LOGITS

Lan

0.52

 المعيارى

0.51

ौर

0.47

lan

0.47

Lam

0.46

lancer

0.46

Lan

0.46

lan

0.45

 <<<<<<<<<<<<<<

0.44

DockStyle

0.43

Activations Density 0.106%

references to specific scientific terms or proper nouns

Tokens starting with "Lan"

Lan as a prefix

No Comments

No Known Activations