INDEX

Explanations

technical terms and phrases related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

تقاوى

-1.02

^(@)

-0.95

 محفوظة

-0.91

$.

-0.84

—

-0.84



-0.82

ViewFeatures

-0.82

>\<^

-0.81

>",

-0.80

°;

-0.79

POSITIVE LOGITS

...

0.86

…

0.76

...

0.75

 piú

0.65

 […]

0.62

…

0.59

 Numerade

0.58

<bos>

0.54

Personensuche

0.53

 [...]

0.53

Activations Density 5.850%

technical terms and phrases related to programming and software development

No Comments

No Known Activations