INDEX

Explanations

references to numerical and statistical details in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Metropolitana

-0.50

 viewDidLoad

-0.50

 LayoutInflater

-0.46

PyErr

-0.45

 onClick

-0.43

onPressed

-0.42

 surgery

-0.42

Hozzáférés

-0.42

 surgeries

-0.41

 BLAST

-0.41

POSITIVE LOGITS

 AssemblyCompany

0.81

исленность

0.76

bootstrapcdn

0.75

XmlAccessType

0.74

windowFixed

0.73

 AssemblyTitle

0.72

DockStyle

0.71

tonode

0.71

 wireType

0.71

UnusedPrivate

0.70

Activations Density 1.175%

references to numerical and statistical details in a document

No Comments

No Known Activations