INDEX

Explanations

terms related to medical and health-related information, particularly statistics and impacts of conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

tamol

-0.55

abetes

-0.50

じる

-0.47

lu

-0.45

sp

-0.43

enderror

-0.42

<strong>

-0.41

umab

-0.41

spa

-0.41

reo

-0.40

POSITIVE LOGITS

 propOrder

0.77

Архівовано

0.74

Efq

0.72

URLException

0.71

exels

0.71

 itſelf

0.70

 himſelf

0.70

 "..\..\

0.69

 myſelf

0.69

 SwitchCompat

0.69

Activations Density 1.366%

terms related to medical and health-related information, particularly statistics and impacts of conditions

No Comments

No Known Activations