INDEX

Explanations

elements related to figures or images in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

RefNanny

-0.58

 насељу

-0.58

 Normdatei

-0.57

 kasarigan

-0.56

Sucesor

-0.50

estacks

-0.47

WRENCE

-0.47

Datuak

-0.47

IonicModule

-0.47

 Италијани

-0.46

POSITIVE LOGITS

Tikang

0.67

LikeLike

0.66

lägen

0.64

 tranſ

0.63

 ſame

0.63

 Theſe

0.62

AddTagHelper

0.62

 ſmall

0.62

 snippetHide

0.61

 Markup

0.61

Activations Density 0.038%

elements related to figures or images in a document

No Comments

No Known Activations