INDEX

Explanations

layout and positioning parameters related to visual boxes or elements

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

 utafitiHapana

-0.59

 autorytatywna

-0.52

Gön

-0.48

EndGlobalSection

-0.46

TagMode

-0.46

 intStringLen

-0.46

expandindo

-0.45

exitRule

-0.44

ᅠ

-0.44

TEMPO

-0.44

POSITIVE LOGITS

!*\

0.46

bitField

0.39

AutoField

0.37

 dAtA

0.35

 تانيه

0.35

írus

0.35

elola

0.35

 Comissão

0.35

 nasel

0.35

RenderAtEndOf

0.33

Activations Density 0.518%

layout and positioning parameters related to visual boxes or elements

No Comments

No Known Activations