INDEX

Explanations

terms related to cancer and malignancy

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

preceding or related to "cancer"

np_acts-logits-general · gemini-2.0-flash

cancer patients and growth

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 &___

-0.79

})()

-0.71

Tay

-0.69

saj

-0.67

 GeoNames

-0.65

InSection

-0.64

Tem

-0.62

CppMethod

-0.61

ipro

-0.60

Stateless

-0.58

POSITIVE LOGITS

 CANCER

0.88

 cancers

0.86

 cancer

0.85

Cancer

0.82

 tumors

0.77

 tumor

0.76

 Cancer

0.76

cancer

0.74

öscht

0.74

Спољашње

0.73

Activations Density 0.199%

terms related to cancer and malignancy

preceding or related to "cancer"

cancer patients and growth

No Comments

No Known Activations