INDEX

Explanations

keywords related to mystery themes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 оригіналу

-0.67

 financeira

-0.58

ForRow

-0.57

 ladle

-0.53

บริการ

-0.53

 liquido

-0.51

 Preparations

-0.51

skins

-0.50

 bicycles

-0.50

 conductance

-0.50

POSITIVE LOGITS

 mystery

2.29

mystery

2.08

 Mystery

2.04

Mystery

1.89

 mysteries

1.60

 misterio

1.25

 puzzle

1.24

 Mysteries

1.19

STERY

1.14

 myster

1.13

Activations Density 0.072%

keywords related to mystery themes in various contexts

No Comments

No Known Activations