INDEX

Explanations

terms linked to specific regulatory or legislative frameworks, particularly in taxation and healthcare

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

 itſelf

-0.69

 Houſe

-0.65

triangleq

-0.64

ſelf

-0.62

 تانيه

-0.62

 Anſ

-0.60

 greateſt

-0.59

 Reſ

-0.58

 Theſe

-0.58

Efq

-0.57

POSITIVE LOGITS

1.25

0.80

（

0.72

 (“

0.62

简称

0.62

 abbreviated

0.61

("

0.58

__':

0.57

]){

0.57

UserScript

0.57

Activations Density 0.588%

terms linked to specific regulatory or legislative frameworks, particularly in taxation and healthcare

No Comments

No Known Activations