INDEX

Explanations

references to stories and narrative elements

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

stories and funny content

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

protoimpl

-0.36

ﬄ

-0.35

jsonwebtoken

-0.34

Measured

-0.33

Ligações

-0.33

<?

-0.32

gathered

-0.32

verifyException

-0.31

heter

-0.31

Notae

-0.31

POSITIVE LOGITS

hoeddwyd

0.58

 Italijanski

0.56

tagHelperRunner

0.56

MLLoader

0.54

WebServlet

0.53

المشاركات

0.48

 Numerade

0.47

UrlResolution

0.46

expandindo

0.46

EndGlobalSection

0.46

Activations Density 0.233%

references to stories and narrative elements

stories and funny content

No Comments

No Known Activations