INDEX

Explanations

terms related to health, specifically focused on body metrics and medical classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

StandardCharsets

-0.69

#+#

-0.65

 MonoBehaviour

-0.65

fromnode

-0.61

 Penh

-0.56

andExpect

-0.56

lamabad

-0.55

/*

-0.53

lichung

-0.53

IActionResult

-0.52

POSITIVE LOGITS

writeField

0.64

$")

0.56

 JAXBElement

0.53

Seznam

0.52

 Wikispecies

0.52

middels

0.52

lardır

0.51

 wireType

0.51

++]

0.50

WithIOException

0.49

Activations Density 1.383%

terms related to health, specifically focused on body metrics and medical classifications

No Comments

No Known Activations