INDEX

Explanations

legal terms and phrases related to medical treatments and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 CreateTagHelper

-0.83

 myſelf

-0.77

 itſelf

-0.76

 whoſe

-0.62

 auffi

-0.60

 poffible

-0.59

 autorytatywna

-0.57

 himſelf

-0.57

 raiſ

-0.55

 themſelves

-0.55

POSITIVE LOGITS

HasColumnType

0.62

 свете

0.56

usepackage

0.54

Ārējās

0.54

Mag

0.53

Tri

0.53

opter

0.52

unek

0.51

nach

0.51

Dy

0.51

Activations Density 1.076%

legal terms and phrases related to medical treatments and conditions

No Comments

No Known Activations