INDEX

Explanations

names of individuals or organizations in specific contexts

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

Text after incomplete sentences

np_acts-logits-general · gemini-2.0-flash

component present, certificate of appealability, validates presence

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.95

-0.92

-0.66

-0.64

-0.61

</h3>

-0.61

and

-0.59

-0.58

on

-0.56

POSITIVE LOGITS

تقاوى

1.40

WebVitals

1.38

 صوتيه

1.35

Hentet

1.31

 Wikimedijinoj

1.31

хьтан

1.30

tvguidetime

1.28

OGND

1.27



1.27

 Савезне

1.25

Activations Density 1.014%

names of individuals or organizations in specific contexts

Text after incomplete sentences

component present, certificate of appealability, validates presence

No Comments

No Known Activations