INDEX

Explanations

words and phrases related to medical conditions and their specific descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 تضيفلها

-0.95



-0.78

 Surname

-0.72

 pstmt

-0.70

 وتسجيلات

-0.68

 ujednoznacz

-0.67

 medulla

-0.67

 condoms

-0.66

 peggio

-0.66

 ddelweddau

-0.66

POSITIVE LOGITS

onic

0.83

letal

0.82

ONIC

0.82

idal

0.80

STIC

0.79

getic

0.78

astic

0.77

gic

0.77

ombic

0.77

lical

0.77

Activations Density 0.706%

words and phrases related to medical conditions and their specific descriptors

No Comments

No Known Activations