INDEX

Explanations

indications of external references or citations in the text

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

Text near figures or tables

np_acts-logits-general · gemini-2.0-flash

case, figure, table, introduction

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onAttach

-0.83

 imageNamed

-0.76

 EconPapers

-0.73

出版年

-0.72

LayoutStyle

-0.69

ftagPool

-0.66

Życiorys

-0.64

 spesa

-0.64

новниш

-0.64

లాలు

-0.63

POSITIVE LOGITS

↵↵

0.73

 noqa

0.69

<eos>

0.57

↵↵↵

0.54

 вікі

0.50

ineno

0.50

↵↵↵↵

0.49

CppMethod

0.48

 Roskov

0.47

ativement

0.46

Activations Density 0.539%

indications of external references or citations in the text

Text near figures or tables

case, figure, table, introduction

No Comments

No Known Activations