INDEX

Explanations

terms related to stroke and its diagnosis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 disponibilités

-0.78

webElementXpaths

-0.75

doms

-0.71

parsedMessage

-0.71

IsMutable

-0.68

reuth

-0.67

KELEY

-0.67

 AspNetCore

-0.67

 referenties

-0.66

brainly

-0.66

POSITIVE LOGITS

Touch

0.78

бе

0.70

 Touch

0.69

touch

0.66

Lin

0.64

Be

0.63

be

0.62

BE

0.61

fa

0.59

Lin

0.58

Activations Density 0.126%

terms related to stroke and its diagnosis

No Comments

No Known Activations