INDEX

Explanations

first-person references and expressions of decision-making

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

I find and buy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 للاسماء

-0.52

<?

-0.50

aarrggbb

-0.49

 AssemblyVersion

-0.48

KommentareTeilen

-0.44

 Walkover

-0.42

íncia

-0.41

#![

-0.41

#+#

-0.40

 thiệu

-0.40

POSITIVE LOGITS

saw

0.65

 searched

0.64

searched

0.59

 search

0.58

 Amazon

0.57

 seen

0.57

 browsing

0.57

saw

0.56

found

0.56

 eBay

0.56

Activations Density 0.028%

first-person references and expressions of decision-making

I find and buy

No Comments

No Known Activations