INDEX

Explanations

specific references to products or features of technology

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

Following "the" in specific contexts

np_acts-logits-general · gemini-2.0-flash

specific nouns after "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

المناصب

-0.70

 utafitiHapana

-0.69

expandindo

-0.68

oa̍t

-0.66

 typelib

-0.62

adaptiveStyles

-0.61

 desmotivaciones

-0.60

EDEFAULT

-0.59

EndContext

-0.58

KommentareTeilen

-0.58

POSITIVE LOGITS

该

0.49

作品

0.47

 product

0.45

 molecule

0.44

 издели

0.44

 creature

0.44

該

0.43

 Pflanze

0.42

这款

0.41

 device

0.40

Activations Density 1.607%

specific references to products or features of technology

Following "the" in specific contexts

specific nouns after "the"

No Comments

No Known Activations