INDEX

Explanations

abbreviations and terms related to medical and health contexts

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

Abbreviations followed by specific letters

np_acts-logits-general · gemini-2.0-flash

SNFTM

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 дописавши

-0.81

 createSlice

-0.68

 <<<<<<<<<<<<<<

-0.58

DropTable

-0.55

PositiveButton

-0.55

<<<<<<<<<<<<

-0.53

TTTT

-0.52

المكان

-0.51

Brainz

-0.51

StructEnd

-0.49

POSITIVE LOGITS

rimônio

0.52

ಿಸ

0.50

".$_

0.49

 Salmo

0.49

 Référence

0.48

jTable

0.48

LEncoder

0.48

knię

0.48

 jSON

0.47

mathrm

0.47

Activations Density 0.337%

abbreviations and terms related to medical and health contexts

Abbreviations followed by specific letters

SNFTM

No Comments

No Known Activations