INDEX

Explanations

instances of identifiers or naming conventions in programming contexts

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

 boards

-0.34

glBindBuffer

-0.33

upol

-0.33

 Boards

-0.32

/******/

-0.32

 Board

-0.32

pyx

-0.32

ozat

-0.32

umnos

-0.32

 smoking

-0.32

POSITIVE LOGITS

 bezeichneter

0.52

ManagedBean

0.49

 AssemblyVersion

0.48

PropertyChanging

0.47

 disambiguazione

0.47

verwijspagina

0.47

Autoritní

0.47

tableFuture

0.46

RequestMapping

0.46

 onOptions

0.46

Activations Density 0.049%

instances of identifiers or naming conventions in programming contexts

No Comments

No Known Activations