INDEX

Explanations

phrases and words related to cause-and-effect relationships

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

Prepositions followed by "the"

np_acts-logits-general · gemini-2.0-flash

markers of resistance

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

 térmico

-0.35

 definitivo

-0.32

 needs

-0.31

 voici

-0.29

 announced

-0.27

jegy

-0.26

 ért

-0.26

 definiti

-0.26

 húmedo

-0.26

shortName

-0.26

POSITIVE LOGITS

RenderAtEndOf

1.02

verifyException

0.82

tagHelperRunner

0.79

aarrggbb

0.75

Jîn

0.72

principalColumn

0.69

 ddelweddau

0.68

sizeCache

0.68

GEBURTS

0.68

 pinulongan

0.66

Activations Density 2.335%

phrases and words related to cause-and-effect relationships

Prepositions followed by "the"

markers of resistance

No Comments

No Known Activations