INDEX

Explanations

financial terms and abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.23

 Jefus

-1.14

 itſelf

-1.14

 ſeveral

-1.10

 beſ

-1.10

 faſt

-1.09

 ſever

-1.08

 himſelf

-1.07

 autorytatywna

-1.07

 themſelves

-1.05

POSITIVE LOGITS

1.30

BN

1.02

0.92

BB

0.88

BA

0.80

BB

0.80

BM

0.77

Bak

0.77

BT

0.75

BH

0.74

Activations Density 0.246%

financial terms and abbreviations

No Comments

No Known Activations