INDEX

Explanations

information related to product pricing and ordering details

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

user context or delimiters

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

+#+#

-0.49

 critica

-0.35

étit

-0.33

MessageOf

-0.32

viated

-0.32

ствий

-0.32

еня

-0.32

eakers

-0.31

ilhas

-0.31

getMinutes

-0.31

POSITIVE LOGITS

 INTERESAR

0.57

VersionUID

0.57

 AssemblyCulture

0.56

niająca

0.51

 AssemblyProduct

0.49

bootstrapcdn

0.49

transQ

0.48

 noDo

0.48

DockStyle

0.47

tvguidetime

0.47

Activations Density 0.005%

information related to product pricing and ordering details

user context or delimiters

No Comments

No Known Activations