INDEX

Explanations

references to characteristics and properties related to biomedical materials and their applications

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

[word] + makes

np_acts-logits-general · gemini-2.0-flash

properties that make

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

migrationBuilder

-0.52

ModelForm

-0.49

Externé

-0.48

__":

-0.46

 <<<<<<<<<<<<<<

-0.45

canActivate

-0.45

twimg

-0.44

LookAnd

-0.44

TagHelper

-0.43

ollectionView

-0.42

POSITIVE LOGITS

 makes

1.52

makes

1.30

 membuatnya

1.30

 Makes

1.19

Makes

1.18

 делает

1.07

 MAKES

1.05

使得

1.04

 make

1.02

 membuat

1.01

Activations Density 0.772%

references to characteristics and properties related to biomedical materials and their applications

[word] + makes

properties that make

No Comments

No Known Activations