INDEX

Explanations

medical terminology and references related to diagnoses and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 useRef

-0.86

AnchorStyles

-0.86

urlpatterns

-0.84

 nahilalakip

-0.84

Brainz

-0.83

artney

-0.83

 nakalista

-0.81

Наводи

-0.81

 Spitz

-0.78

 referenties

-0.78

POSITIVE LOGITS

 McCullough

0.86

 Wils

0.82

Varint

0.76

 Hodgson

0.75

 Whyte

0.74

tek

0.74

:#

0.74

gon

0.72

miary

0.72

 dets

0.71

Activations Density 2.136%

medical terminology and references related to diagnoses and treatments

No Comments

No Known Activations