INDEX

Explanations

references to tools, processes, and techniques related to programming and technology

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

specific technical nouns

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

PointerException

-0.42

omiast

-0.41

 hObject

-0.38

Brows

-0.38

 Alquiler

-0.38

 aban

-0.38

ronpa

-0.38

湾

-0.37

 Sina

-0.37

Gön

-0.36

POSITIVE LOGITS

 صوتيه

0.59

تقاوى

0.50

bitField

0.44

Obrázky

0.41

 beginnetje

0.41

 iNdEx

0.41

ffilm

0.41

AISSEE

0.40

GEBURTSDATUM

0.39

 PyLong

0.38

Activations Density 0.087%

references to tools, processes, and techniques related to programming and technology

specific technical nouns

No Comments

No Known Activations