INDEX

Explanations

code-related terms and class definitions in programming

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

IUrlHelper

-0.71

 CreateTagHelper

-0.66

()]);

-0.64

AndEndTag

-0.63

PreferredItem

-0.63

featureID

-0.61

 للاسماء

-0.59

aarrggbb

-0.59

esez

-0.57

"]);

-0.56

POSITIVE LOGITS

Билгалдахарш

0.70

 rospy

0.69

 createContext

0.58

Lähteet

0.55

 ComVisible

0.48

rzost

0.48

由於

0.47

OnInit

0.47

 CGSize

0.47

JSONException

0.47

Activations Density 0.908%

code-related terms and class definitions in programming

No Comments

No Known Activations