INDEX

Explanations

technical terms related to software or system components

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

user input parameters or code directives

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

<eos>

-0.30

joy

-0.28

<b>

-0.28

öglichkeiten

-0.27

<i>

-0.27

قبال

-0.26

readAs

-0.25

fat

-0.25

__":

-0.24

POSITIVE LOGITS

SBATCH

5.31

InjectAttribute

0.98

 للاسماء

0.94

dafx

0.93

WithIOException

0.89

httphttps

0.86

WebServlet

0.86

ArgumentParser

0.85

 nahilalakip

0.85

StructEnd

0.81

Activations Density 0.000%

technical terms related to software or system components

user input parameters or code directives

No Comments

No Known Activations