INDEX

Explanations

the use of numbers, variables, and references in academic and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.44

↵↵

-0.39

ach

-0.39

me

-0.38

Competition

-0.37

 univerz

-0.37

—

-0.37

 Competition

-0.37

lad

-0.37

POSITIVE LOGITS

ValueStyle

1.27

 חיצוניים

1.07

TintMode

1.04

InputBorder

0.99

 صوتيه

0.93

dafx

0.92

 cherchés

0.92

rrggbb

0.91

 autorytatywna

0.91

脚注の使い方

0.88

Activations Density 0.252%

the use of numbers, variables, and references in academic and technical contexts

No Comments

No Known Activations