INDEX

Explanations

terms related to computational frameworks or programming structures

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

Abbreviations, often followed by parentheses

np_acts-logits-general · gemini-2.0-flash

words starting with V

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.54

脚注の使い方

-0.53

 ThreadPool

-0.49

addCriterion

-0.45

ød

-0.45

 Picchu

-0.44

 skai

-0.44

nė

-0.44

ⓧ

-0.43

 autorytatywna

-0.43

POSITIVE LOGITS

1.02

1.00

 Vice

0.95

 vanadium

0.94

VP

0.93

Vice

0.93

 vice

0.93

VP

0.92

Activations Density 1.205%

terms related to computational frameworks or programming structures

Abbreviations, often followed by parentheses

words starting with V

No Comments

No Known Activations