INDEX

Explanations

lines of code or segments within programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

TagMode

-1.05

SequentialGroup

-0.99

 autorytatywna

-0.89

 estekak

-0.77

saraba

-0.77

 RouterModule

-0.76

CloseOperation

-0.75

 GenerationType

-0.73

ConstraintMaker

-0.73

GraphicsUnit

-0.72

POSITIVE LOGITS

enderror

0.56

 idéia

0.54

 assunto

0.54

jspx

0.49

gabung

0.46

<eos>

0.46

 peines

0.46

Anybody

0.45

 Others

0.45

 mueve

0.45

Activations Density 0.038%

lines of code or segments within programming constructs

No Comments

No Known Activations