INDEX

Explanations

references to legal terminology or components of legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tikang

-0.94

 مرئيه

-0.75

MessageTagHelper

-0.59

 isInitialized

-0.57

 учё

-0.53

hasMoreElements

-0.51

 тобой

-0.50

tió

-0.49

ason

-0.47

laszt

-0.47

POSITIVE LOGITS

 whoſe

0.80

 houſe

0.77

 ―――――

0.72

 uſe

0.72

<?

0.71

**

0.71

 faſt

0.71

 ſtate

0.71

ſy

0.71

">${

0.70

Activations Density 0.434%

references to legal terminology or components of legal cases

No Comments

No Known Activations