INDEX

Explanations

data structures and references related to legal cases or software documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

 ویکی‌پدی

-0.53

 AssemblyProduct

-0.51

">—

-0.49

 Wikimédia

-0.48

 uVar

-0.47

WireFormatLite

-0.47

scriptcase

-0.46

期刊论文

-0.45

 mercies

-0.45

 Reiner

-0.45

POSITIVE LOGITS

fjspx

0.59

sizeCache

0.58

 متعلقه

0.58

DockStyle

0.57

 poveznice

0.54

 autorytatywna

0.53

UpInside

0.53

contentLoaded

0.51

NullCheck

0.51

 lenker

0.49

Activations Density 1.893%

data structures and references related to legal cases or software documentation

No Comments

No Known Activations