INDEX

Explanations

references to debugging information in a technical or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

őre

-0.46

思い

-0.45

xmlhttp

-0.43

RenderAtEndOf

-0.42

webElement

-0.41

()))

-0.40

detectChanges

-0.40

ri

-0.39

 فريبيس

-0.39

dis

-0.38

POSITIVE LOGITS

 AssemblyTitle

1.00

Efq

0.88

 Jefus

0.85

 itſelf

0.84

 houſe

0.83

ſelf

0.82

 myſelf

0.82

TagMode

0.82

@"/

0.82

 Houſe

0.80

Activations Density 0.404%

references to debugging information in a technical or programming context

No Comments

No Known Activations