INDEX

Explanations

coding structures and elements relevant to data processing and attribute manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AccessorTable

-0.46

'{@

-0.43

plish

-0.41

يًا

-0.40

RuleContext

-0.40

entibus

-0.39

 zeichnet

-0.39

itism

-0.38

UFACT

-0.38

HandlerContext

-0.37

POSITIVE LOGITS

Personensuche

0.57

0.55

.*")]

0.50

 виправивши

0.50

 Normdatei

0.47

 camion

0.45

يكب

0.44

AutoScale

0.44

convertView

0.42

 referrerpolicy

0.42

Activations Density 1.594%

coding structures and elements relevant to data processing and attribute manipulation

No Comments

No Known Activations