INDEX

Explanations

terms related to health and medical 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

 Drapeau

-0.75

JsonHelper

-0.66

 שוליים

-0.66

 ioutil

-0.62

RegistryLite

-0.60

erializer

-0.57

tedra

-0.56

ništvo

-0.56

jde

-0.56

 ويكيميديا

-0.56

POSITIVE LOGITS

int

1.09

int

0.96

 Integer

0.92

INT

0.83

 integer

0.79

Int

0.79

Int

0.78

INT

0.78

Integer

0.75

setInt

0.74

Activations Density 2.873%

terms related to health and medical conditions

No Comments

No Known Activations