INDEX

Explanations

elements related to user interaction and content engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 figliu

-0.64

 ocasi

-0.61

 morire

-0.54

 Nachweis

-0.53

SharedCtor

-0.52

attendre

-0.52

 ajutor

-0.51

 tempio

-0.51

 siguran

-0.50

 edição

-0.50

POSITIVE LOGITS

tvguidetime

0.80

 pinulongan

0.77

webElementGuid

0.71

nloa

0.66

 getSource

0.64

 autorytatywna

0.62

 InputDecoration

0.62

SupportActionBar

0.62



0.61

databind

0.60

Activations Density 0.124%

elements related to user interaction and content engagement

No Comments

No Known Activations