INDEX

Explanations

references to specific dates and numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Бахар

-0.75

AccessorTable

-0.75

 AssemblyCulture

-0.67

#+#

-0.65

GEBURTSDATUM

-0.62

Tē

-0.59

SharedCtor

-0.57

 parseFrom

-0.56

 tiegħek

-0.55

 onResponse

-0.54

POSITIVE LOGITS

enumi

0.56

luia

0.51

口水

0.51

脚注の使い方

0.50

OGND

0.48

MOUTH

0.48

skr

0.48

<eos>

0.45

furan

0.45

ikiki

0.45

Activations Density 0.155%

references to specific dates and numbers

No Comments

No Known Activations