INDEX

Explanations

references to smallness or something being diminutive

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AndEndTag

-0.62

大型

-0.51

 Пото

-0.50

 ampio

-0.49

>`;

-0.49

 internetowa

-0.49

 Pág

-0.49

Étape

-0.49

 utama

-0.49

 StatefulWidget

-0.48

POSITIVE LOGITS

(<

1.09

 tiny

0.90

 insignificant

0.89

🤏

0.82

pox

0.74

 sized

0.74

Tiny

0.72

 size

0.71

cule

0.71

小的

0.69

Activations Density 0.365%

references to smallness or something being diminutive

No Comments

No Known Activations