INDEX

Explanations

keywords related to programming constructs and libraries

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

code block keywords

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

Negative Logits

GraphicsUnit

-0.58

+#+

-0.57

 يتيمه

-0.56

 صوتيه

-0.51

ConstraintMaker

-0.49

новниш

-0.47



-0.47

+#+#

-0.46

GeoNames

-0.46

 AssemblyCompany

-0.46

POSITIVE LOGITS

IUrlHelper

0.58

fputs

0.41

Mike

0.39

 Behavioral

0.38

 Mike

0.38

lei

0.38

用

0.37

behavioral

0.37

 Extensions

0.36

thenes

0.36

Activations Density 0.019%

keywords related to programming constructs and libraries

code block keywords

No Known Activations