INDEX

Explanations

structured data elements or code syntax

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

<start_of_turn>user

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

-0.36

目

-0.31

ตรี

-0.31

合わせて

-0.31

mi

-0.31

 quedando

-0.31

 Schmid

-0.30

The

-0.30

ตา

-0.30

POSITIVE LOGITS

 nahilalakip

0.93

 Roskov

0.85

ésultats

0.85

 informée

0.81

 Italijanski

0.81

FunctionFlags

0.80

ðsíða

0.79

 autorytatywna

0.79

iſen

0.79

AndEndTag

0.79

Activations Density 0.000%

structured data elements or code syntax

<start_of_turn>user

No Comments

No Known Activations