INDEX

Explanations

terms related to medical regulations and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

chein

-0.53

.*")]

-0.51

mettre

-0.49

IZONT

-0.49

ENGER

-0.48

pere

-0.47

 öne

-0.47

 Mans

-0.46

ężczy

-0.45

Mit

-0.44

POSITIVE LOGITS

 Normdatei

0.78

ⓧ

0.76

 CURLOPT

0.72

GEBURTSDATUM

0.71

rungsseite

0.68

 CreateTagHelper

0.62

AndEndTag

0.60

 мәкал

0.60

OGND

0.60

WriteTagHelper

0.57

Activations Density 1.424%

terms related to medical regulations and definitions

No Comments

No Known Activations