INDEX

Explanations

patterns of mathematical relationships and dependencies in data

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

Efq

-1.27

 myſelf

-1.17

 Jefus

-1.16

 Majefty

-1.13

Eſ

-1.11

 Monfieur

-1.07

 pleaſure

-1.06

 reaſon

-1.06

 ―――――

-1.04

 purpoſe

-1.03

POSITIVE LOGITS

0.90

0.80

0.69

“

0.69

re

0.66

0.65

0.63

die

0.63

0.62

Activations Density 0.494%

patterns of mathematical relationships and dependencies in data

No Comments

No Known Activations