INDEX

Explanations

code-related syntax and structures, specifically focusing on data structures and types

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

ſelves

-0.58

AndEndTag

-0.58

 Exacts

-0.57

 itſelf

-0.53

LEncoder

-0.49

 Inſ

-0.49

Демографія

-0.47

gants

-0.47

 Anſ

-0.47

 pleaſure

-0.47

POSITIVE LOGITS

 either

0.41

 lección

0.38

 interactiva

0.38

 deliciosos

0.36

Története

0.35

 habido

0.35

 sección

0.35

 artificiales

0.34

 clásicos

0.33

 defaultstate

0.32

Activations Density 0.783%

code-related syntax and structures, specifically focusing on data structures and types

No Comments

No Known Activations