INDEX

Explanations

keywords and terms related to programming frameworks and user interface components

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

ngx views programming context

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

 Audiodateien

-0.59

 nahilalakip

-0.53

الحياه

-0.53

Tikang

-0.49

 estekak

-0.49

ecap

-0.46

 dAtA

-0.46

 transfieras

-0.45

 getRule

-0.45

 برانيه

-0.44

POSITIVE LOGITS

AccessorTable

0.58

IBOutlet

0.55

 betweenstory

0.54

ftc

0.49

pmd

0.48

XtraReports

0.47

ModelSerializer

0.47

tinyos

0.46

Dış

0.46

PROLOG

0.46

Activations Density 0.012%

keywords and terms related to programming frameworks and user interface components

ngx views programming context

No Comments

No Known Activations