INDEX

Explanations

references to tags and their importance in text

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

"Tag" or "tagged" followed by another word

np_acts-logits-general · gemini-2.0-flash

tag archives or tagged entries

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

 تانيه

-0.74

exprimer

-0.72

wright

-0.71

 Illustrations

-0.66

mpy

-0.65

Inhoud

-0.60

ristiano

-0.59

 Reverso

-0.59

']));

-0.59

POSITIVE LOGITS

tag

1.66

 tags

1.66

Tag

1.57

tags

1.44

TAG

1.44

 Tags

1.44

Tag

1.39

WithTag

1.29

 tagging

1.26

Tags

1.25

Activations Density 0.118%

references to tags and their importance in text

"Tag" or "tagged" followed by another word

tag archives or tagged entries

No Comments

No Known Activations