INDEX

Explanations

elements related to programming and document structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 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

 itself

-0.55

 this

-0.54

addComponent

-0.54

prüfung

-0.53

is

-0.53

Semitism

-0.51

 does

-0.49

 happens

-0.48

Everything

-0.48

vermögen

-0.48

POSITIVE LOGITS

 những

1.18

Những

1.11

 Những

1.11

những

1.09

 Theſe

1.08

mga

1.06

那些

1.02

 egne

0.99

autres

0.93

 those

0.93

Activations Density 0.063%

elements related to programming and document structure

No Comments

No Known Activations