INDEX

Explanations

terms related to medical evaluations and assessments

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

λ

-0.96

lambda

-0.95

λ

-0.95

 lambda

-0.92

 Lambda

-0.89

Lam

-0.87

 Wilkins

-0.79

Lam

-0.79

Wil

-0.79

WIL

-0.78

POSITIVE LOGITS

 Arth

0.94

Arth

0.80

 Hanley

0.79

 Iberia

0.78

 Arthur

0.76

 arth

0.73

 Holloway

0.73

Arthur

0.69

 Merlin

0.68

Sai

0.67

Activations Density 1.164%

terms related to medical evaluations and assessments

No Comments

No Known Activations