INDEX

Explanations

references and citations 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

RenderAtEndOf

-0.67

IntoConstraints

-0.67

 vuitton

-0.57

Vidite

-0.55

 farmaco

-0.55

rektur

-0.52

 '=',

-0.52

?>/

-0.51

Hochspringen

-0.50

yyr

-0.50

POSITIVE LOGITS

 оригіналу

0.62

IonicModule

0.57

 unknownFields

0.55

terung

0.54

ITest

0.51

hibits

0.50

 imageNamed

0.49

Fes

0.49

 Avent

0.46

 originals

0.46

Activations Density 0.068%

references and citations in texts

No Comments

No Known Activations