INDEX

Explanations

code comments and documentation headers in scripts or programming files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

principalTable

-0.68

точник

-0.53

 refuser

-0.53

 amélior

-0.53

AlterField

-0.52

 képes

-0.52

 deberes

-0.51

 oubli

-0.51

 émissions

-0.51

 Vande

-0.50

POSITIVE LOGITS

webElement

0.74

//

0.72

dise

0.69

/*

0.62

--]

0.62

AnchorStyles

0.62

/*---

0.61

 Handy

0.57

="//

0.57

//**

0.57

Activations Density 0.362%

code comments and documentation headers in scripts or programming files

No Comments

No Known Activations