INDEX

Explanations

function definitions and methods related to resetting and clearing operations

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

clears, resets, removes

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

UserScript

-0.50

styleType

-0.47

RTEE

-0.46

 BrowserModule

-0.45

Vidite

-0.44

HasAnnotation

-0.44

DataBinding

-0.41

ьаж

-0.40

Catching

-0.40

BrowserModule

-0.39

POSITIVE LOGITS

 صوتيه

0.53

*/].

0.47

ToBounds

0.38

 فريبيس

0.38



0.38

*/}

0.36

 Suecia

0.36

 betweenstory

0.36

Sucesor

0.36

publicain

0.35

Activations Density 0.012%

function definitions and methods related to resetting and clearing operations

clears, resets, removes

No Comments

No Known Activations