INDEX

Explanations

definitions and formal statements in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

.*")]

-0.72

 esternos

-0.69

="@+

-0.68

exels

-0.67

UrlResolution

-0.65

 كمان

-0.65

IsPostBack

-0.65

 InputDecoration

-0.65

 الحره

-0.64

getSeconds

-0.63

POSITIVE LOGITS

 estimés

0.55

NgModule

0.49

ropa

0.49

Хро

0.48

 Sodom

0.45

=>

0.44

ഈ

0.44

องค์

0.43

 Савез

0.43

 Epis

0.43

Activations Density 0.070%

definitions and formal statements in a scientific context

No Comments

No Known Activations