INDEX

Explanations

phrases that denote definitions or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 estoppel

-0.44

 morte

-0.43

Siddhartha

-0.43

']))

-0.42

 atheism

-0.42

 acrobat

-0.39

bü

-0.38

 shook

-0.38

 чере

-0.38

timo

-0.37

POSITIVE LOGITS

HasForeignKey

0.90

 sogenannte

0.89

 called

0.89

 sogenannten

0.86

called

0.85

NUMX

0.85

 Called

0.84

Called

0.82

 termed

0.81

extAlignment

0.76

Activations Density 0.560%

phrases that denote definitions or classifications

No Comments

No Known Activations