INDEX

Explanations

keywords related to medical procedures and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Dresden

-0.65

VPC

-0.61

 Hopper

-0.57

 Allende

-0.56

||}

-0.56

 gynhyrchwyd

-0.55

 Saxon

-0.53

TAGE

-0.52

胥

-0.52

 parch

-0.52

POSITIVE LOGITS

 fruits

0.91

 otomatig

0.90

 Bear

0.88

 Pipe

0.87

SharedCtor

0.87

Leo

0.86

 Piper

0.85

Bear

0.83

 BEAR

0.82

 piper

0.81

Activations Density 3.321%

keywords related to medical procedures and geographic locations

No Comments

No Known Activations