INDEX

Explanations

medical terms and related concepts within discussions of health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

and

-1.05

 ***!

-0.71

 either

-0.70

either

-0.64

 TextAppearance

-0.63

 totiž

-0.61

الإنجليزية

-0.61

 nemlig

-0.61

UnitTesting

-0.60

 neither

-0.59

POSITIVE LOGITS

 alike

0.82

 consiguiente

0.76

 lainnya

0.72

何より

0.70

/")

0.68

 whatnot

0.67

 importantly

0.65

それに

0.65

 Exacts

0.65

Activations Density 0.712%

medical terms and related concepts within discussions of health

No Comments

No Known Activations