INDEX

Explanations

instances of high-frequency tokens or markers in programming code

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

EDEFAULT

-0.83

 AssemblyCulture

-0.79

RenderAtEndOf

-0.76

LookAnd

-0.75

principalColumn

-0.74

StoryboardSegue

-0.72

IndentedString

-0.71

parsedMessage

-0.71

complexContent

-0.69

XmlAccessorType

-0.69

POSITIVE LOGITS

marginHorizontal

0.40

仔

0.34

 gracios

0.32

pherson

0.31

 template

0.30

 perplexing

0.30

 claras

0.29

 parcialmente

0.28

 tesis

0.28

Activations Density 0.099%

instances of high-frequency tokens or markers in programming code

No Comments

No Known Activations