INDEX

Explanations

import statements in code

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

Python import statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ResumeLayout

-0.50

 protoimpl

-0.39

endphp

-0.38

@"/

-0.37

<bos>

-0.37

@[+][

-0.37

EndInit

-0.37

GraphicsUnit

-0.37

harapkan

-0.36

EYE

-0.36

POSITIVE LOGITS

import

1.02

 import

0.70

IMPORTED

0.65

 Import

0.65

 Signalez

0.53

imported

0.52

 importer

0.51

 imported

0.50

 impor

0.49

OMR

0.49

Activations Density 0.000%

import statements in code

Python import statements

No Comments

No Known Activations