INDEX

Explanations

sections of a document marked by HTML tags, specifically headers and lists, indicating structural information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 محفوظة

-0.69

 utafitiHapana

-0.66

 vPvB

-0.62

 AspNetCore

-0.60

躇

-0.57

sidemargin

-0.56

 ComVisible

-0.56

 دیکھیے

-0.55

 autorytatywna

-0.55

SqlClient

-0.54

POSITIVE LOGITS

CATEGORY

0.51

 απε

0.51

GOTREF

0.51

 pédagogique

0.49

amaño

0.48

歹

0.48

 varandra

0.48

OFFICIAL

0.48

汰

0.47

enumii

0.47

Activations Density 0.034%

sections of a document marked by HTML tags, specifically headers and lists, indicating structural information

No Comments

No Known Activations