INDEX

Explanations

elements that indicate a legal or procedural framework

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

 propOrder

-1.00

Vidite

-0.88

'));

-0.84

labus

-0.84

CloseOperation

-0.80

mybatisplus

-0.77

omitempty

-0.77

AccessorTable

-0.77

IsMutable

-0.77

"]);

-0.76

POSITIVE LOGITS

0.52

 rather

0.51

 tantum

0.50

0.49

扱い

0.49

 nature

0.47

 stát

0.47

 intended

0.47

 noqa

0.46

 riconos

0.46

Activations Density 0.458%

elements that indicate a legal or procedural framework

No Comments

No Known Activations