INDEX

Explanations

references to edges in graphical representations or network structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ьаж

-0.51

setVerticalGroup

-0.50

UnitId

-0.43

AccessFile

-0.43

 Retail

-0.43

BeginInit

-0.43

DMETHOD

-0.43

 تضيفلها

-0.42

 ExecuteAsync

-0.42

verifyException

-0.41

POSITIVE LOGITS

 edge

1.38

edge

1.23

Edge

1.16

 Edge

1.13

EDGE

1.07

 EDGE

1.05

 fees

0.97

 edges

0.94

edges

0.87

 edged

0.86

Activations Density 0.048%

references to edges in graphical representations or network structures

No Comments

No Known Activations