INDEX

Explanations

terms related to medical conditions and procedural terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Alyssa

-0.91

Paz

-0.86

putInt

-0.84

ulkner

-0.84

 Sass

-0.83

 Gior

-0.82

mtext

-0.81

mingbird

-0.81

mtable

-0.80

 Lutz

-0.79

POSITIVE LOGITS

 Pont

0.86

Pont

0.76

er

0.76

 McKnight

0.74

Vod

0.73

Rams

0.72

 allu

0.70

wc

0.70

 Solana

0.68

vation

0.67

Activations Density 1.967%

terms related to medical conditions and procedural terminology

No Comments

No Known Activations