INDEX

Explanations

terms related to cancer and tumors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

CppMethod

-0.70

Uli

-0.67

Tem

-0.67

Tem

-0.66

mutlich

-0.66

hoeddwyd

-0.66

 GeoNames

-0.65

Tay

-0.65

ǔ

-0.64

 getopt

-0.64

POSITIVE LOGITS

 cancer

2.04

 Cancer

1.80

Cancer

1.74

 CANCER

1.70

cancer

1.63

 cancers

1.57

 cancerous

1.22

癌症

1.12

 kanker

1.08

 malignancy

1.07

Activations Density 0.139%

terms related to cancer and tumors

No Comments

No Known Activations