INDEX

Explanations

references to locations and infrastructure related to transportation and railways

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

Location or position descriptions

np_acts-logits-general · gemini-2.0-flash

named or unnamed features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

PyExc

-0.80

出版年

-0.77

WebVitals

-0.73

 виправивши

-0.71

 للمعارف

-0.69

<tbody>

-0.67

 FetchType

-0.67

 ویکی‌پدیای

-0.65

styleType

-0.65

 مشين

-0.63

POSITIVE LOGITS

 tidligere

0.55

 adjacent

0.54

 adjoining

0.53

 rechter

0.52

 formerly

0.52

 parcialmente

0.51

 ehemalige

0.51

 overgrown

0.51

 unnamed

0.50

Unnamed

0.49

Activations Density 0.353%

references to locations and infrastructure related to transportation and railways

Location or position descriptions

named or unnamed features

No Comments

No Known Activations