INDEX

Explanations

names and terms related to individuals or groups involved in significant activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 ویکی‌پدیا

-0.63

bibinfo

-0.61

bibfield

-0.58

первых

-0.57

BibitemShut

-0.57

 Paix

-0.57

енча

-0.56

šech

-0.55

 Theſe

-0.54

 חיצוניים

-0.53

POSITIVE LOGITS

Xna

0.82

AsUp

0.79

SizeF

0.78

 للمعارف

0.75

دانشنامهٔ

0.70

LLocation

0.70

mybatisplus

0.69

THISDAY

0.68

 مرئيه

0.67

 محفوظة

0.67

Activations Density 0.523%

names and terms related to individuals or groups involved in significant activities or events

No Comments

No Known Activations