INDEX

Explanations

terms related to medical therapies and mechanisms of action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Bernstein

-0.74

 Lenny

-0.72

 Franks

-0.70

Kub

-0.69

 Berner

-0.68

Waw

-0.68

 Stanley

-0.67

 Skull

-0.66

Kub

-0.66

 Franck

-0.65

POSITIVE LOGITS

Wei

0.92

Wei

0.89

Kuz

0.80

 Kristina

0.77

 Jefferson

0.76

 Kura

0.73

SOR

0.71

Aes

0.70

Jefferson

0.68

Kuz

0.68

Activations Density 1.689%

terms related to medical therapies and mechanisms of action

No Comments

No Known Activations