INDEX

Explanations

references to programming constructs and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

PyErr

-0.54

 OnInit

-0.53

 tampon

-0.52

óngase

-0.52

 démocr

-0.51

SBATCH

-0.51

 Scherer

-0.51

EEG

-0.51

ardez

-0.50

nextProps

-0.49

POSITIVE LOGITS

--)

0.65

LabelTagHelper

0.60

دانشنامهٔ

0.59

}}=$

0.56

://$

0.53

")){

0.53

 ostavi

0.52

'):

0.52

DoubleQuotes

0.52

principalColumn

0.52

Activations Density 0.140%

references to programming constructs and libraries

No Comments

No Known Activations