INDEX

Explanations

references to arrays in a programming context

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

array and table

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

AndEndTag

-0.41

 rospy

-0.40

WebServlet

-0.39

 "..\..\..\

-0.39

StatusBadRequest

-0.36

الدراسه

-0.36

lapsingToolbar

-0.36

 "..\..\

-0.35

LogFactory

-0.34

 inner

-0.33

POSITIVE LOGITS

NSDictionary

0.58

 array

0.58

ToArray

0.58

 arrays

0.55

 LinkedHashMap

0.55

 FormData

0.54

数组

0.54

 Array

0.54

isArray

0.54

 iParam

0.53

Activations Density 0.009%

references to arrays in a programming context

array and table

No Comments

No Known Activations