INDEX

Explanations

references to specific individuals, particularly names associated with events or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

 ModelExpression

-0.56

ValueStyle

-0.50

windowFixed

-0.49

DIPSETTING

-0.48

########.

-0.43

tslib

-0.42

 EconPapers

-0.40

QMetaType

-0.38

 INTERESAR

-0.38

setArguments

-0.37

POSITIVE LOGITS

 Byrne

0.65

 Gallagher

0.64

 Brennan

0.64

 Ryan

0.64

 Flynn

0.63

 Flanagan

0.63

 Reilly

0.63

 Fitzpatrick

0.63

 Connolly

0.62

 Doherty

0.62

Activations Density 0.440%

references to specific individuals, particularly names associated with events or organizations

No Comments

No Known Activations