INDEX

Explanations

sections labeled as abstracts in documents

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

abstract:

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

$_"

-0.93

 occaf

-0.93

ьаж

-0.93

 ſtate

-0.92

 houſe

-0.91

 Reſ

-0.88

 pleaſure

-0.88

 Мексичка

-0.86

 perſon

-0.86

 betweenstory

-0.85

POSITIVE LOGITS

Abstract

0.74

 Abstract

0.60

abstract

0.57

abstractmethod

0.55

 ABSTRACT

0.54

 abstract

0.52

ABSTRACT

0.50

摘要

0.48

 summary

0.48

 Abstracts

0.46

Activations Density 0.024%

sections labeled as abstracts in documents

abstract:

No Comments

No Known Activations