INDEX

Explanations

terms related to data types and programming structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

UnusedPrivate

-0.72

enumi

-0.70

principalTable

-0.64

 Administrativna

-0.64

 للاسماء

-0.63

 تضيفلها

-0.63

 صوتيه

-0.62

aarrggbb

-0.61

enumii

-0.60

XmlAccessType

-0.60

POSITIVE LOGITS

1.39

1.33

WS

1.31

WS

1.28

WW

1.21

Ws

1.20

Waw

1.20

WM

1.19

WR

1.19

WI

1.19

Activations Density 3.634%

terms related to data types and programming structures

No Comments

No Known Activations