INDEX

Explanations

actions related to modifications and instructions, particularly focusing on restrictions and best practices in technical or procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

RegistryLite

-0.66

 GoogleFonts

-0.55

 vuitton

-0.55

 Toen

-0.54

 Parac

-0.53

 ICommand

-0.52

abinieri

-0.51

الإنجليزية

-0.50

 Euphrates

-0.50

ualaikum

-0.50

POSITIVE LOGITS

any

0.84

 quelconque

0.73

nor

0.72

ANY

0.66

any

0.66

 anymore

0.65

too

0.63

 anyone

0.62

or

0.62

有任何

0.62

Activations Density 0.584%

actions related to modifications and instructions, particularly focusing on restrictions and best practices in technical or procedural contexts

No Comments

No Known Activations