INDEX

Explanations

names associated with various types of legal proceedings and terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ModelSerializer

-0.74

top

-0.54

top

-0.50

 sqlalchemy

-0.49

tual

-0.48

 setas

-0.47

vast

-0.47

iecie

-0.47

tml

-0.46

queryInterface

-0.46

POSITIVE LOGITS

 InputDecoration

0.79

новниш

0.65

enumii

0.60

Демографія

0.59

:✨

0.58

 سكانية

0.58

#+#

0.56

 gubern

0.56

]")]

0.55

 فريبيس

0.54

Activations Density 0.098%

names associated with various types of legal proceedings and terminologies

No Comments

No Known Activations