INDEX

Explanations

programming constructs and data structures related to API responses and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

adaptiveStyles

-0.75

AndEndTag

-0.73

\{\\

-0.72

posedge

-0.69

//

-0.69

 <=",

-0.67

Demografie

-0.64

Enllaces

-0.63

 Exacts

-0.63

ConverterFactory

-0.61

POSITIVE LOGITS

jspx

0.53

]_

0.45

望

0.44

 коло

0.43

cito

0.43

ntz

0.41

RegistryLite

0.41

 تنظ

0.40

ۇ

0.40

 initComponents

0.39

Activations Density 0.274%

programming constructs and data structures related to API responses and data handling

No Comments

No Known Activations