INDEX

Explanations

references to time periods or spatial relationships

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

 about

-0.51

on

-0.50

 against

-0.48

out

-0.47

 within

-0.47

 into

-0.47

 with

-0.46

 from

-0.46

in

-0.46

by

-0.46

POSITIVE LOGITS

 Between

1.52

 Around

1.50

Between

1.45

 Across

1.44

 Through

1.44

Through

1.41

Around

1.34

Across

1.34

 Against

1.32

Against

1.28

Activations Density 0.231%

references to time periods or spatial relationships

No Comments

No Known Activations