INDEX

Explanations

structured data related to software or programming elements

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

file paths with core or app

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.43

Personendaten

-0.40

 sustained

-0.38

 تضيفلها

-0.37

://$

-0.35

)})

-0.35

 Infórmanos

-0.34

PullParser

-0.34

Gambas

-0.33

)}}{

-0.33

POSITIVE LOGITS

 rospy

0.56

Referanser

0.56

Izvori

0.50

EndContext

0.47

PhysRev

0.44

yntaxException

0.44

KommentareTeilen

0.44

enderror

0.44

 لينك

0.44

maxcdn

0.43

Activations Density 0.013%

structured data related to software or programming elements

file paths with core or app

No Comments

No Known Activations