INDEX

Explanations

instructions related to functionalities 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 @ 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

ViewFeatures

-0.54

RectangleBorder

-0.43

ScreenState

-0.43

AutoScaleMode

-0.42

msgTypes

-0.42

InSection

-0.41

styleable

-0.41

offsetof

-0.40

 bezeichneter

-0.39

 Dames

-0.39

POSITIVE LOGITS

ConstraintMaker

0.52

 surla

0.47

 swojego

0.47

oredCriteria

0.47

 vastly

0.46

httphttps

0.46

 vectorielle

0.45

TagMode

0.45

 ervoor

0.43

 dieß

0.42

Activations Density 0.701%

instructions related to functionalities and processes

No Comments

No Known Activations