INDEX

Explanations

references to general concepts or items that are significant or noteworthy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

AnchorStyles

-0.96

 pleaſure

-0.89

 myſelf

-0.86

 juſ

-0.85

 ſtate

-0.83

 Jefus

-0.83

 ſtre

-0.83

 uſe

-0.82

 viſ

-0.80

 ſta

-0.80

POSITIVE LOGITS

 thing

1.37

 things

1.36

 Thing

1.34

 THING

1.30

Things

1.28

 Things

1.25

 THINGS

1.24

Thing

1.21

things

1.10

THING

0.96

Activations Density 0.080%

references to general concepts or items that are significant or noteworthy

No Comments

No Known Activations