INDEX

Explanations

references to examples and inclusivity in discussions

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 houſe

-0.82

 purpoſe

-0.76

 MainAxisSize

-0.70

 fubject

-0.66

 ſtate

-0.66

⋙

-0.63

 singularities

-0.62

 finitely

-0.62

yntaxException

-0.61

 penetrates

-0.61

POSITIVE LOGITS

0.54

stens

0.54

Max

0.54

max

0.52

the

0.52

 finding

0.52

 keeping

0.51

hit

0.50

>*/

0.50

re

0.48

Activations Density 0.104%

references to examples and inclusivity in discussions

No Comments

No Known Activations