INDEX

Explanations

instances of the word "plant."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

LookAnd

-0.57

SaveChangesAsync

-0.56

expandindo

-0.54

httphttps

-0.48

+#+

-0.47

Gweler

-0.45

Baden

-0.45

lepaskan

-0.44

цездатний

-0.44

moveToNext

-0.43

POSITIVE LOGITS

 wallet

0.61

 workshops

0.58

 workshop

0.57

 Plant

0.56

 plant

0.55

 werden

0.53

 wallets

0.52

Workshop

0.50

 végét

0.48

 jury

0.48

Activations Density 0.168%

instances of the word "plant."

No Comments

No Known Activations