INDEX

Explanations

references to programming concepts, particularly related to data types and variable declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 names

-0.76

 itemName

-0.69

 productName

-0.65

itemName

-0.64

 newName

-0.63

 Name

-0.60

 name

-0.60

 Names

-0.59

ItemName

-0.58

 serviceName

-0.58

POSITIVE LOGITS

 CreateTagHelper

0.84

TabIndex

0.71

 number

0.69

 aantal

0.64

 nargin

0.62

 hashCode

0.61

CloseOperation

0.61

parseInt

0.59

principalColumn

0.59

statusCode

0.59

Activations Density 0.291%

references to programming concepts, particularly related to data types and variable declarations

No Comments

No Known Activations