INDEX

Explanations

code-related keywords and constructs used in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Backman

-0.39

-0.38

-0.34

 gereken

-0.33

 Schulte

-0.32

พาะ

-0.30

 selepas

-0.30

 quizá

-0.29

 devenu

-0.29

 manifiesto

-0.29

POSITIVE LOGITS

 FontWeight

1.04

 Shakspeare

0.96



0.94

<unused41>

0.92

<unused43>

0.92

<unused74>

0.92

<unused79>

0.92

<unused8>

0.92

 ſei

0.92

<pad>

0.91

Activations Density 0.350%

code-related keywords and constructs used in programming languages

No Comments

No Known Activations