INDEX

Explanations

medical and biological terms related to processes 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 @ 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

 autorytatywna

-0.88

osoba

-0.68

rigos

-0.61

 betweenstory

-0.59

úgó

-0.59

 bezeichneter

-0.59

atég

-0.59

tamol

-0.59

躇

-0.58

 Gazetteer

-0.58

POSITIVE LOGITS

0.67

KommentareTeilen

0.66

łek

0.52

wikimedia

0.52

מד

0.52

xt

0.51

 suon

0.50

 kasarigan

0.49

ļas

0.47

DateString

0.47

Activations Density 2.587%

medical and biological terms related to processes and conditions

No Comments

No Known Activations