INDEX

Explanations

commands and command-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

AutoScale

-0.45

脚注の使い方

-0.40

évaluateur

-0.40

 reír

-0.39

 TAMBÉM

-0.38

SequentialGroup

-0.37

 schlechte

-0.37

 Straßen

-0.34

########.

-0.34

 falsche

-0.34

POSITIVE LOGITS

 Command

0.59

 ICommand

0.57

cmd

0.56

 виправивши

0.52

Rob

0.52

 Prompt

0.51

 Commands

0.50

ExecuteReader

0.50

 comand

0.50

 prompt

0.50

Activations Density 0.094%

commands and command-related terminology

No Comments

No Known Activations