INDEX

Explanations

SQL-related keywords and terms associated with databases and queries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

nya

-1.42

ness

-1.32

ための

-0.71

not

-0.70

它

-0.68

อีก

-0.67

อย่าง

-0.65

很

-0.63

ため

-0.62

อาจ

-0.61

POSITIVE LOGITS

ٔ

0.89

eee

0.81

eeee

0.81

eeeee

0.80

0.79

eeeeeeee

0.75

eeeeee

0.69

urope

0.62

ee

0.59

iro

0.57

Activations Density 3.979%

SQL-related keywords and terms associated with databases and queries

No Comments

No Known Activations