INDEX

Explanations

conjunctions and references to potential scenarios or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

PerformLayout

-0.74

 GenerationType

-0.69

তথ্যসূত্র

-0.67

elemField

-0.67

 lenker

-0.64

出版年

-0.64

Atsauces

-0.62

Allora

-0.62

mander

-0.61

IContainer

-0.61

POSITIVE LOGITS

AccessorTable

0.54

zeba

0.50

 happens

0.47

 Happens

0.47

 geluk

0.46

bentar

0.46

多い

0.45

 sucede

0.44

 operativo

0.43

PYX

0.43

Activations Density 0.368%

conjunctions and references to potential scenarios or evidence

No Comments

No Known Activations