INDEX

Explanations

procedural instructions related to software usage and commands

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

Text after a period or quotation mark

np_acts-logits-general · gemini-2.0-flash

context menu

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

AddTagHelper

-0.85

AccessorTable

-0.61

tagHelperRunner

-0.54

SequentialGroup

-0.53

$_['

-0.50

fjspx

-0.49

########.

-0.48

')")

-0.48

 CanadaChoose

-0.48

 kasarigan

-0.47

POSITIVE LOGITS

 damit

0.40

ebabkan

0.40

 reveals

0.39

 instantly

0.38

FailureListener

0.37

 discloses

0.37

RTLU

0.36

 then

0.35

 generates

0.34

 angew

0.34

Activations Density 0.606%

procedural instructions related to software usage and commands

Text after a period or quotation mark

context menu

No Comments

No Known Activations