INDEX

Explanations

references to authorship or attribution in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

VersionUID

-0.51

 amarela

-0.50

getvalue

-0.49

 étrangères

-0.47

bewerken

-0.47

istic

-0.45

bbero

-0.45

 Hanford

-0.45

GraphicsUnit

-0.44

 بندی

-0.44

POSITIVE LOGITS

 means

1.59

 virtue

1.41

way

1.31

standers

1.31

means

1.29

 MEANS

1.17

stander

1.12

Means

1.07

 dint

1.05

 Means

1.03

Activations Density 0.333%

references to authorship or attribution in texts

No Comments

No Known Activations