INDEX

Explanations

terms related to medical conditions and their symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 sanitaires

-0.78

 Orrell

-0.77

 MotionEvent

-0.74

 Whitehall

-0.73

coque

-0.72

theless

-0.72

powiedz

-0.72

LookAnd

-0.72

 spelt

-0.72

úly

-0.70

POSITIVE LOGITS

 glasses

0.86

 Munch

0.83

 Milne

0.81

Burton

0.78

Jio

0.78

 Mulder

0.77

 Milner

0.77

 Guna

0.75

 Mubarak

0.72

 estn

0.72

Activations Density 2.137%

terms related to medical conditions and their symptoms

No Comments

No Known Activations