INDEX

Explanations

programming-related keywords and language attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-0.68

kæ

-0.57

 hendes

-0.57

 mulighed

-0.56

 acima

-0.52

 direção

-0.52

 Duckworth

-0.49

Géographie

-0.49

Capítulo

-0.49

Cyfeiriadau

-0.49

POSITIVE LOGITS

AddHtmlAttribute

5.99

WriteAttribute

1.49

+:+

0.99

AccessFile

0.81

 насељу

0.80

 pinulongan

0.77

 AppCompatTheme

0.76

interopRequire

0.76

RectangleBorder

0.76

SourceChecksum

0.74

Activations Density 0.009%

programming-related keywords and language attributes

No Comments

No Known Activations