INDEX

Explanations

references to figures and data visualization elements in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

__':

-0.45

 doty

-0.45

__':

-0.40

⏮

-0.37

yscy

-0.36

devamını

-0.35

ronpa

-0.35

automat

-0.35

évaluateur

-0.35

 defaultstate

-0.34

POSITIVE LOGITS

 figures

2.47

 figure

2.36

fig

2.36

 Figures

2.11

figure

2.05

figures

2.05

fig

2.03

 figura

2.02

 FIGURES

1.99

Figures

1.94

Activations Density 0.323%

references to figures and data visualization elements in text

No Comments

No Known Activations