INDEX

Explanations

Arabic script characters and symbols

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

Mathematical or foreign notation/symbols

np_acts-logits-general · gemini-2.0-flash

mathematical or technical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

on

-0.59

in

-0.57

-0.56

-0.54

-0.53

-0.51

is

-0.50

-0.48

im

-0.47

POSITIVE LOGITS

AccessorTable

1.25

GraphicsUnit

1.20

 nahilalakip

1.20

 فريبيس

1.19

 '\\;'

1.16

PerformLayout

1.13

LookAnd

1.13

]--;

1.11

 HasFactory

1.09

 BoxFit

1.09

Activations Density 0.006%

Arabic script characters and symbols

Mathematical or foreign notation/symbols

mathematical or technical notation

No Comments

No Known Activations