INDEX

Explanations

code snippets and data processing references

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

Diwedd

-0.59

RTGC

-0.57

ьажоргаш

-0.56

PyExc

-0.54

 CreateTagHelper

-0.51

 ویکی‌پدی

-0.49

principalColumn

-0.48

UnsafeEnabled

-0.47

 setOpen

-0.47

 involves

-0.46

POSITIVE LOGITS

 ModelExpression

0.46

Hentet

0.45

currentColor

0.43

GOTREF

0.40

 transfieras

0.38

Personensuche

0.37

 mentales

0.36

theoremstyle

0.36

SerializedName

0.36

asinya

0.35

Activations Density 0.193%

code snippets and data processing references

No Comments

No Known Activations