INDEX

Explanations

terms related to programming and sharing functionality in applications

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

sharing, trial, learned, promise

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

 greedy

-0.33

 stri

-0.32

 appeared

-0.32

GIVEREF

-0.32

 greed

-0.31

PARA

-0.31

 Ache

-0.31

uminum

-0.31

lwjgl

-0.30

SignedIn

-0.30

POSITIVE LOGITS

RenderAtEndOf

0.85

 kasarigan

0.69

 CreateTagHelper

0.64

bufio

0.59

 noDo

0.56

 disambiguazione

0.55

">//

0.52

 OFDb

0.52

 propOrder

0.51

AccessorTable

0.51

Activations Density 0.162%

terms related to programming and sharing functionality in applications

sharing, trial, learned, promise

No Comments

No Known Activations