INDEX

Explanations

descriptive insights about concepts and detailed concepts in various subjects

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

Follows prepositions or adjectives

np_acts-logits-general · gemini-2.0-flash

detailed description

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCompany

-0.80

 typelib

-0.72

GraphicsUnit

-0.66

UrlResolution

-0.63

 ویکی‌پدی

-0.62

ConstraintMaker

-0.62

AISSEE

-0.61

 AssemblyProduct

-0.61

 Normdatei

-0.59

GIVEREF

-0.59

POSITIVE LOGITS

 wholesome

0.41

MemberId

0.40

 Glaser

0.38

</h2>

0.38

bg

0.37

 recent

0.37

 recommendations

0.36

InMemory

0.36

 Driscoll

0.36

 Recommendations

0.36

Activations Density 2.394%

descriptive insights about concepts and detailed concepts in various subjects

Follows prepositions or adjectives

detailed description

No Comments

No Known Activations