INDEX

Explanations

references to specific technical components or metrics in a scientific context

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

location names and affiliations

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

Geplaatst

-0.73

 ویکی‌پدی

-0.71

 wireType

-0.71

IsMutable

-0.68

 propOrder

-0.67

رشف

-0.67

 kaarangay

-0.66

uxxxx

-0.65

 мәкал

-0.60

setVerticalGroup

-0.59

POSITIVE LOGITS

memberof

0.41

Dettagli

0.36

来自

0.35

Več

0.34

QG

0.33

ค

0.33

 chez

0.33

ม้

0.32

 của

0.31

 examples

0.30

Activations Density 0.279%

references to specific technical components or metrics in a scientific context

location names and affiliations

No Comments

No Known Activations

references to specific technical components or metrics in a scientific context

location names and affiliations

No Comments

No Known Activations