INDEX

Explanations

proper nouns, particularly names, locations, and significant terms related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 kasarigan

-1.06

LookAnd

-0.92

 صوتيه

-0.88

AsUp

-0.84

 TextAppearance

-0.79

 ویکی‌پدیا

-0.78

AccessorTable

-0.75

 المعيارى

-0.74

 للاسماء

-0.73

 ModelExpression

-0.71

POSITIVE LOGITS

 figliu

0.51

 battre

0.46

 orologio

0.46

 morire

0.45

WebServlet

0.45

ніципалі

0.43

 znam

0.42

 artificiales

0.42

ftc

0.41

transQ

0.40

Activations Density 0.536%

proper nouns, particularly names, locations, and significant terms related to events

No Comments

No Known Activations