INDEX

Explanations

references to legal cases or court decisions

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

 CURIAM

-0.84

 AssemblyVersion

-0.76

oa̍t

-0.76

 مشين

-0.73

TagMode

-0.72

transQ

-0.70

ValueStyle

-0.70

 препратки

-0.69

 Administrativna

-0.68

ftagPool

-0.68

POSITIVE LOGITS

gatsby

0.50

setCharacter

0.50

TacToe

0.46

0.43

<bos>

0.43

 adoption

0.42

meleon

0.41

裹

0.41

diğimiz

0.41

0.40

Activations Density 0.427%

references to legal cases or court decisions

No Comments

No Known Activations