INDEX

Explanations

references to puzzles and puzzle-solving mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 polvere

-0.51

govina

-0.50

原始内容存档于

-0.49

xffff

-0.46

 néglig

-0.46

 bohat

-0.46

Gep

-0.45

KHR

-0.45

EMT

-0.45

ragamo

-0.45

POSITIVE LOGITS

 puzzle

1.43

 puzzles

1.31

 solve

1.31

 solving

1.29

 clues

1.23

 Puzzle

1.22

 solved

1.20

 Solve

1.20

 solvers

1.19

 solver

1.18

Activations Density 0.245%

references to puzzles and puzzle-solving mechanisms

No Comments

No Known Activations