INDEX

Explanations

keywords and functions related to selection, display, and manipulation of data in programming contexts

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

command verbs followed by objects

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

 represented

-0.36

is

-0.35

on

-0.33

as

-0.33

 haberse

-0.33

 geçi

-0.31

 intend

-0.31

in

-0.31

POSITIVE LOGITS

 transfieras

0.82

 мәкалә

0.75

$_"

0.75

extAlignment

0.72

$_(

0.71

 queſta

0.71

httphttps

0.69

tagHelperRunner

0.69

 betweenstory

0.68

 Мексичка

0.67

Activations Density 0.081%

keywords and functions related to selection, display, and manipulation of data in programming contexts

command verbs followed by objects

No Comments

No Known Activations