INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

to

-0.53

 Blue

-0.46

 blue

-0.46

 extra

-0.45

 test

-0.44

 long

-0.43

no

-0.43

mo

-0.42

 lour

-0.42

 memas

-0.40

POSITIVE LOGITS

AsUp

0.76

})*/

0.69

otry

0.68

 endwhile

0.66

taxia

0.66

 jsPsych

0.65

 plexus

0.65

✨:

0.65

SceneManagement

0.65

 Meksiku

0.64

Activations Density 0.224%

mathematical expressions and symbols

No Comments

No Known Activations