INDEX

Explanations

numerical ratings or scores related to evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 confess

-0.56

 confessed

-0.51

 confession

-0.49

 Achtung

-0.48

 admit

-0.47

uckt

-0.46

 murm

-0.45

TProtocol

-0.45

Cyfeiriadau

-0.45

 призна

-0.44

POSITIVE LOGITS

0.80

parsedMessage

0.72

__*/

0.65

extAlignment

0.65

ellido

0.64

 OnInit

0.61

yntaxException

0.60

EndContext

0.60

 Audiodateien

0.60

 máxima

0.59

Activations Density 0.146%

numerical ratings or scores related to evaluations

No Comments

No Known Activations