INDEX

Explanations

references to speeches, lectures, and public addresses

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

zmir

-0.50

 tradizione

-0.48

textAppearance

-0.48

気に入りの

-0.48

 productores

-0.45

isLoaded

-0.45

 silenzio

-0.42

formik

-0.42

 Gegenteil

-0.42

 coûte

-0.42

POSITIVE LOGITS

 lectures

1.11

 lecture

1.09

 speeches

1.07

 Lectures

1.07

 keynote

1.03

 sermons

1.02

 sermon

1.01

 Lecture

0.99

 presentations

0.98

 speech

0.91

Activations Density 0.369%

references to speeches, lectures, and public addresses

No Comments

No Known Activations