INDEX

Explanations

specific attributes and behaviors associated with characters or actors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

con

-0.47

-0.43

-0.42

or

-0.41

<eos>

-0.41

-0.40

</

-0.40

Parameterized

-0.40

be

-0.40

POSITIVE LOGITS

 myſelf

1.47

 Monfieur

1.42

 themſelves

1.35

 itſelf

1.32

 himſelf

1.29

 ſtate

1.29

 purpoſe

1.25

 Jefus

1.22

 Reſ

1.20

 '\\;'

1.19

Activations Density 0.340%

specific attributes and behaviors associated with characters or actors in various contexts

No Comments

No Known Activations