INDEX

Explanations

occurrences of programming language import statements

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

import android

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

Ä

-0.34

 hence

-0.31

 veiks

-0.29

 Derfor

-0.29

nyttet

-0.29

 عش

-0.28

<eos>

-0.27

 asimismo

-0.26

 Hence

-0.25

 Asimismo

-0.25

POSITIVE LOGITS

BeginInit

0.90

fjspx

0.88

 CreateTagHelper

0.88

 propOrder

0.88

IndentedString

0.87

WriteTagHelper

0.83

IUrlHelper

0.82

mybatisplus

0.81

<unused41>

0.81

<unused43>

0.81

Activations Density 0.001%

occurrences of programming language import statements

import android

No Comments

No Known Activations