INDEX

Explanations

symbols and formatting in technical or scientific writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

enumi

-0.87

enumii

-0.56

Sam

-0.55

entin

-0.54

ım

-0.53

gra

-0.52

weck

-0.52

うちに

-0.51

har

-0.50

EMOS

-0.50

POSITIVE LOGITS

 تضيفلها

0.70

 AppColors

0.62

CTP

0.62

DeleteBehavior

0.61

UIControlState

0.58

 houſe

0.58

 AssemblyCulture

0.57

ViewFeatures

0.57

 onPostExecute

0.57

 pymongo

0.57

Activations Density 0.013%

symbols and formatting in technical or scientific writing

No Comments

No Known Activations