INDEX

Explanations

programming terms and variables related to data structures and object properties

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

code completion and assignments

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.96

IBOutlet

-0.69

帖最后由

-0.68

webElementXpaths

-0.67

ViewChild

-0.65

msgTypes

-0.64

 dAtA

-0.63

MessageOf

-0.63

fromnode

-0.62

Tembelea

-0.61

POSITIVE LOGITS

0.45

Lato

0.41

 probably

0.39

 kurikulum

0.38

 correa

0.36

 Grecs

0.35

lewati

0.35

oció

0.34

 Mungkin

0.34

Activations Density 0.001%

programming terms and variables related to data structures and object properties

code completion and assignments

No Comments

No Known Activations