INDEX

Explanations

the term "equivalent" and related phrases indicating similarity or equivalence

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

equivalent of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 téléchargez

-0.51

PDE

-0.49

catch

-0.48

JOH

-0.47

 Locks

-0.47

 inoxydable

-0.46

 Charities

-0.46

$_['

-0.45

спи

-0.45

maxLines

-0.45

POSITIVE LOGITS

 equivalent

2.39

equivalent

2.17

Equivalent

2.11

 Equivalent

2.11

 equivalente

1.75

 equivalents

1.64

 equival

1.34

 equivalence

1.31

 équi

1.31

 equivalently

1.23

Activations Density 0.010%

the term "equivalent" and related phrases indicating similarity or equivalence

equivalent of

No Comments

No Known Activations