INDEX

Explanations

terms and concepts related to cancer

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

webElementXpaths

-0.73

bpy

-0.68

Tay

-0.64

 GeoNames

-0.64

Tem

-0.64

 kasarigan

-0.63

hoeddwyd

-0.62

셨

-0.61

Uli

-0.60

 getopt

-0.60

POSITIVE LOGITS

 cancer

2.36

 Cancer

2.10

Cancer

2.01

cancer

1.97

 CANCER

1.96

 cancers

1.76

 cancerous

1.39

癌症

1.36

 kanker

1.29

 cáncer

1.26

Activations Density 0.100%

terms and concepts related to cancer

No Comments

No Known Activations