INDEX

Explanations

specific medical or biological terms related to diagnostics and pathology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 silêncio

-0.89

 contextLoads

-0.88

 colchón

-0.80

 morire

-0.79

 scattata

-0.76

gunas

-0.74

 asciug

-0.74

 bicchiere

-0.74

 ospiti

-0.73

 inmueble

-0.73

POSITIVE LOGITS

auso

0.94

ugo

0.94

llo

0.86

0.84

Xeno

0.84

Bello

0.84

ITO

0.82

 Munro

0.81

Klo

0.81

васто

0.80

Activations Density 3.028%

specific medical or biological terms related to diagnostics and pathology

No Comments

No Known Activations