INDEX

Explanations

terms related to installation processes and technical references

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

 habet

-0.29

ModelSerializer

-0.28

 dess

-0.28

Kanpo

-0.28

FunctionFlags

-0.27

 contrase

-0.26

PropertyChanged

-0.26

SOUNDBITE

-0.25

 hjälp

-0.25

SharedModule

-0.25

POSITIVE LOGITS

 surla

0.73

$_=

0.69

ंदीखरीदारी

0.66

 ſeinem

0.66

 Menſchen

0.66

𑄮

0.66

 deſſen

0.65

𓂸

0.65

 daysTop

0.65

𑄨

0.65

Activations Density 0.070%

terms related to installation processes and technical references

No Comments

No Known Activations