INDEX

Explanations

terms related to web and cloud services

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

expression networks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

UnusedPrivate

-0.54

yym

-0.54

 doInBackground

-0.52

 actionPerformed

-0.51

 Wikimedijinoj

-0.50

WebVitals

-0.47

 BoxFit

-0.47

RenderAtEndOf

-0.45

__(/*!

-0.45

POSITIVE LOGITS

readline

1.88

signin

1.02

 readline

0.81

cloudflare

0.66

Autoritní

0.53

 signin

0.46

 CanadaChoose

0.46

Signin

0.44

nextLine

0.43

vaal

0.43

Activations Density 0.001%

terms related to web and cloud services

expression networks

No Comments

No Known Activations