INDEX

Explanations

references to data structures and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

UnusedPrivate

-0.59

complexType

-0.56

 NSCoder

-0.54

TagMode

-0.52

 Audiodateien

-0.51

 AssemblyCulture

-0.49

 AssemblyTitle

-0.47

舺

-0.46

 ویکی‌پدیای

-0.45

 مشين

-0.44

POSITIVE LOGITS

Насе

0.40

ercizi

0.37

 cases

0.35

ollectionView

0.35

errHandler

0.34

 Taktlose

0.34

ocha

0.34

 scrap

0.34

 parmi

0.34

 berken

0.34

Activations Density 0.286%

references to data structures and their classifications

No Comments

No Known Activations