INDEX

Explanations

clinical terms and references related to medical conditions and injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 onboarding

-1.10

-0.93

 impactful

-0.90

nullptr

-0.87

COVID

-0.86

 COVID

-0.86

 LGBTQ

-0.83

 playbook

-0.83

-0.80

⁠

-0.80

POSITIVE LOGITS

 daß

1.14

 muß

1.05

 Daß

1.01

 läßt

0.98

faßt

0.91

 müßte

0.85

 skall

0.81

 Einfluß

0.80

 mußte

0.78

 mußten

0.74

Activations Density 0.755%

clinical terms and references related to medical conditions and injuries

No Comments

No Known Activations