INDEX

Explanations

references to government and its associated activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 EconPapers

-1.27

__":

-1.16

 unknownFields

-1.09

ConstraintMaker

-1.05

 snippetHide

-1.05

UnitTesting

-1.02

MemoryWarning

-1.02

 Normdatei

-1.01

ChildScrollView

-1.00

__":

-0.98

POSITIVE LOGITS

 government

0.76

 GOVERNMENT

0.64

 Government

0.61

Government

0.60

gov

0.58

 governments

0.57

GOVERNMENT

0.53

 govt

0.51

government

0.48

 governmental

0.47

Activations Density 0.495%

references to government and its associated activities

No Comments

No Known Activations