INDEX

Explanations

proper nouns and names, particularly those related to authors and affiliations

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

preceding citations

np_acts-logits-general · gemini-2.0-flash

mohan stated

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

break

-1.00

 break

-0.91

 breaks

-0.82

 CreateTagHelper

-0.79

breaks

-0.74

GraphicsUnit

-0.71

 Break

-0.71

Break

-0.71

 Breaks

-0.70

存于互联网档案馆

-0.68

POSITIVE LOGITS

XmlAccessType

0.43

0.42

var

0.42

Pas

0.41

wat

0.40

pas

0.40

pas

0.40

Mediabestanden

0.40

itope

0.39

 actrice

0.39

Activations Density 0.170%

proper nouns and names, particularly those related to authors and affiliations

preceding citations

mohan stated

No Comments

No Known Activations