INDEX

Explanations

references to individuals and their connections to events or positions of authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ImageContext

-0.75

SequentialGroup

-0.74

 NSCoder

-0.69

WriteTagHelper

-0.64

#+#

-0.61



-0.60

//

-0.58

SourceChecksum

-0.54

kuuta

-0.51

MessageTagHelper

-0.51

POSITIVE LOGITS

HideFlags

0.66

FXMLLoader

0.55

DebuggerStep

0.50

 intStringLen

0.50

 kaarangay

0.47

alek

0.45

Tembelea

0.44

ждений

0.44

voerd

0.44

contentLoaded

0.44

Activations Density 0.292%

references to individuals and their connections to events or positions of authority

No Comments

No Known Activations