INDEX

Explanations

technical and programming-related terms, specifically related to data processing and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

tgz

-0.34

AED

-0.32

AIT

-0.31

thâu

-0.31

NES

-0.31

AO

-0.30

WAN

-0.30

AED

-0.29

Mr

-0.28

MCA

-0.28

POSITIVE LOGITS

 unknownFields

0.66

⤹

0.56

出版年

0.54

তথ্যসূত্র

0.54

setVerticalGroup

0.54

HasIndex

0.53

istoitu

0.53

 APPROPRI

0.53

 realisation

0.51

sizeCache

0.51

Activations Density 0.003%

technical and programming-related terms, specifically related to data processing and structures

No Comments

No Known Activations