INDEX

Explanations

references to statistical or numerical data

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

 AssemblyCulture

-0.65

setVerticalGroup

-0.59

 Normdatei

-0.59

tagHelperRunner

-0.59

IBOutlet

-0.57

formik

-0.56

NAK

-0.55

bewerken

-0.54

 nonatomic

-0.54

apunov

-0.54

POSITIVE LOGITS

 kuulu

0.57

 通販

0.55

vraagd

0.55

 bağı

0.55

 Timoteo

0.54

 AppModule

0.54

 permanently

0.54

UnifiedTopology

0.54

 fotografico

0.54

__":

0.53

Activations Density 0.087%

references to statistical or numerical data

No Comments

No Known Activations