INDEX

Explanations

terms related to utility and offensive spells or abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

SpringRunner

-0.53

apnews

-0.50

 Oltre

-0.50

Coordonnées

-0.47

TextWatcher

-0.46

 BoxFit

-0.43

]='\

-0.42

 juuri

-0.42

 stof

-0.42

 stepwise

-0.40

POSITIVE LOGITS

 Paglinawan

0.73

 CreateTagHelper

0.73

PrototypeOf

0.72

GEBURTSDATUM

0.67

 Date

0.62

awtextra

0.61

djangoproject

0.61

 QtCore

0.61

Poloha

0.60

atype

0.60

Activations Density 0.501%

terms related to utility and offensive spells or abilities

No Comments

No Known Activations