INDEX

Explanations

programming-related terms and expressions used in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 defaultstate

-0.57

 HttpNotFound

-0.57

 resourceCulture

-0.54

 chrétien

-0.53

 enfans

-0.52

 linkovi

-0.51

 ModelExpression

-0.51

fortawesome

-0.49

 '\\;'

-0.49

RenderAtEndOf

-0.49

POSITIVE LOGITS

BERTO

0.47

spec

0.44

king

0.43

ONI

0.43

 متعلقه

0.42

down

0.41

ษัท

0.41

oni

0.41

fra

0.41

ter

0.41

Activations Density 0.244%

programming-related terms and expressions used in code

No Comments

No Known Activations