INDEX

Explanations

indicators of health conditions and medical symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 frühen

-0.44

ngOn

-0.41

 Núñez

-0.40

 Versuch

-0.40

 Burch

-0.40

exécution

-0.40

 arşivlendi

-0.39

但也

-0.39

 carico

-0.39

uidado

-0.39

POSITIVE LOGITS

<>

0.57

 Houſe

0.56

tagHelperRunner

0.56

unknownFields

0.54

፩

0.53

"],

0.52

ſelves

0.52

ſelf

0.51

++){

0.51

 ſta

0.50

Activations Density 0.115%

indicators of health conditions and medical symptoms

No Comments

No Known Activations