INDEX

Explanations

phrases that express similarity or comparison

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

Efq

-0.87

 ſever

-0.84

 Majefty

-0.83

 fevere

-0.80

bewerken

-0.80

 Rukh

-0.78

 StatelessWidget

-0.77

 ſeveral

-0.77

حياته

-0.77

 purpoſe

-0.75

POSITIVE LOGITS

 como

1.66

 comme

1.66

 như

1.35

 як

1.29

Como

1.27

 jako

1.26

 как

1.25

como

1.24

 kaip

1.21

wie

1.20

Activations Density 0.186%

phrases that express similarity or comparison

No Comments

No Known Activations