INDEX

Explanations

function return statements across various programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

or

-0.46

 prior

-0.45

 meaning

-0.43

 Absicht

-0.43

prior

-0.42

 also

-0.42

Prior

-0.42

 πρά

-0.41

 Schall

-0.41

كما

-0.41

POSITIVE LOGITS

 مشين

1.03

Datuak

1.01

SourceChecksum

0.97

脚注の使い方

0.92

writeFieldEnd

0.92

MemoryWarning

0.91

addContainerGap

0.83

 AssemblyCulture

0.82

findpost

0.81

RectangleBorder

0.81

Activations Density 0.060%

function return statements across various programming languages

No Comments

No Known Activations