INDEX

Explanations

references to figures or illustrations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Tsub

-0.73

 csal

-0.70

Sapp

-0.66

loadAll

-0.65

 myſelf

-0.64

Osp

-0.63

 traditionnels

-0.63

Ast

-0.63

 Sopho

-0.62

önt

-0.62

POSITIVE LOGITS

 Figure

1.66

Figure

1.64

 figures

1.63

 Figures

1.62

 figure

1.60

 FIGURES

1.56

Figures

1.48

figure

1.47

 Figueroa

1.41

 FIGURE

1.41

Activations Density 0.183%

references to figures or illustrations in the text

No Comments

No Known Activations