INDEX

Explanations

references to API and configuration management in code

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

api

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

Personendaten

-0.75

windowFixed

-0.51

 AssemblyCompany

-0.47

 فريبيس

-0.45

KommentareTeilen

-0.45

rungsseite

-0.42

disposing

-0.42

parsedMessage

-0.41

principalTable

-0.41

AutoField

-0.40

POSITIVE LOGITS

Vidite

0.56

 Commerce

0.48

 commerce

0.43

疾

0.40

 propellant

0.40

web

0.40

orthand

0.40

 мәкалә

0.39

 NIST

0.39

ệng

0.39

Activations Density 0.003%

references to API and configuration management in code

api

No Comments

No Known Activations