INDEX

Explanations

code-related structures and commands across programming languages

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

tvguidetime

-1.08

 متعلقه

-0.98

 disambiguazione

-0.95

 Мексичка

-0.87

expandindo

-0.81

IsContent

-0.80

 cherchés

-0.79

 /\.(

-0.78

XMLSchema

-0.78

GEBURTS

-0.77

POSITIVE LOGITS

↵↵

0.49

次第

0.44

Ge

0.44

vo

0.42

Ges

0.42

</tr>

0.42

 Then

0.40

0.39

The

0.39

Activations Density 0.071%

code-related structures and commands across programming languages

No Comments

No Known Activations