INDEX

Explanations

personal experiences and feedback related to products and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

CloseOperation

-0.46

getMenuInflater

-0.42

AndEndTag

-0.39

 represen

-0.34

 vulgares

-0.34

aturi

-0.34

 виправивши

-0.33

 Vikipedi

-0.33

warf

-0.33

 compare

-0.33

POSITIVE LOGITS

ftagPool

0.68

UserScript

0.53

impianto

0.51

 Inscrivez

0.49

 '\\;'

0.47

лтамалар

0.47

usermodel

0.47

TintMode

0.46

ItemBackground

0.46

 >=",

0.45

Activations Density 0.553%

personal experiences and feedback related to products and processes

No Comments

No Known Activations